A brief guide to multi-objective reinforcement learning and planning JAAMAS track
- Hayes, Conor, Bargiacchi, Eugenio, Källström, Johan, Macfarlane, Matthew, Reymond, Mathieu, Verstraeten, Timothy, Zintgraf, Luisa, Dazeley, Richard, Heintz, Frederik, Howley, Enda, Irissappane, Aathirai, Mannion, Patrick, Nowé, Ann, Ramos, Gabriel, Restelli, Marcello, Vamplew, Peter, Roijers, Diederik
- Authors: Hayes, Conor , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederik , Howley, Enda , Irissappane, Aathirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023, London, 29 May to 2 June 2023, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS Vol. 2023-May, p. 1988-1990
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple - often conflicting - objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results. This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper [4], serves as a guide for the application of explicitly multi-objective methods to difficult problems. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
- Authors: Hayes, Conor , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederik , Howley, Enda , Irissappane, Aathirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2023
- Type: Text , Conference paper
- Relation: 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023, London, 29 May to 2 June 2023, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS Vol. 2023-May, p. 1988-1990
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are usually complex, and require trade-offs between multiple - often conflicting - objectives. However, the majority of research in reinforcement learning (RL) and decision-theoretic planning assumes a single objective, or that multiple objectives can be handled via a predefined weighted sum over the objectives. Such approaches may oversimplify the underlying problem, and produce suboptimal results. This extended abstract outlines the limitations of using a semi-blind iterative process to solve multi-objective decision making problems. Our extended paper [4], serves as a guide for the application of explicitly multi-objective methods to difficult problems. © 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
A conceptual framework for externally-influenced agents: an assisted reinforcement learning review
- Bignold, Adam, Cruz, Francisco, Taylor, Matthew, Brys, Tim, Dazeley, Richard, Vamplew, Peter, Foale, Cameron
- Authors: Bignold, Adam , Cruz, Francisco , Taylor, Matthew , Brys, Tim , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Ambient Intelligence and Humanized Computing Vol. 14, no. 4 (2023), p. 3621-3644
- Full Text:
- Reviewed:
- Description: A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent’s performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
- Authors: Bignold, Adam , Cruz, Francisco , Taylor, Matthew , Brys, Tim , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Ambient Intelligence and Humanized Computing Vol. 14, no. 4 (2023), p. 3621-3644
- Full Text:
- Reviewed:
- Description: A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent’s performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
A multi-objective deep reinforcement learning framework
- Nguyen, Thanh, Nguyen, Ngoc, Vamplew, Peter, Nahavandi, Saeid, Dazeley, Richard, Lim, Chee
- Authors: Nguyen, Thanh , Nguyen, Ngoc , Vamplew, Peter , Nahavandi, Saeid , Dazeley, Richard , Lim, Chee
- Date: 2020
- Type: Text , Journal article
- Relation: Engineering Applications of Artificial Intelligence Vol. 96, no. (2020), p.
- Full Text:
- Reviewed:
- Description: This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental results on two benchmark problems (two-objective deep sea treasure environment and three-objective Mountain Car problem) indicate that the proposed framework is able to find the Pareto-optimal solutions effectively. The proposed framework is generic and highly modularized, which allows the integration of different deep reinforcement learning algorithms in different complex problem domains. This therefore overcomes many disadvantages involved with standard multi-objective reinforcement learning methods in the current literature. The proposed framework acts as a testbed platform that accelerates the development of MODRL for solving increasingly complicated multi-objective problems. © 2020 Elsevier Ltd
- Authors: Nguyen, Thanh , Nguyen, Ngoc , Vamplew, Peter , Nahavandi, Saeid , Dazeley, Richard , Lim, Chee
- Date: 2020
- Type: Text , Journal article
- Relation: Engineering Applications of Artificial Intelligence Vol. 96, no. (2020), p.
- Full Text:
- Reviewed:
- Description: This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental results on two benchmark problems (two-objective deep sea treasure environment and three-objective Mountain Car problem) indicate that the proposed framework is able to find the Pareto-optimal solutions effectively. The proposed framework is generic and highly modularized, which allows the integration of different deep reinforcement learning algorithms in different complex problem domains. This therefore overcomes many disadvantages involved with standard multi-objective reinforcement learning methods in the current literature. The proposed framework acts as a testbed platform that accelerates the development of MODRL for solving increasingly complicated multi-objective problems. © 2020 Elsevier Ltd
A nethack learning environment language wrapper for autonomous agents
- Goodger, Nikolaj, Vamplew, Peter, Foale, Cameron, Dazeley, Richard
- Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Open Research Software Vol. 11, no. (2023), p.
- Full Text:
- Reviewed:
- Description: This paper describes a language wrapper for the NetHack Learning Environment (NLE) [1]. The wrapper replaces the non-language observations and actions with comparable language versions. The NLE offers a grand challenge for AI research while MiniHack [2] extends this potential to more specific and configurable tasks. By providing a language interface, we can enable further research on language agents and directly connect language models to a versatile environment. © 2023 The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See http://creativecommons.org/licenses/by/4.0/.
- Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Open Research Software Vol. 11, no. (2023), p.
- Full Text:
- Reviewed:
- Description: This paper describes a language wrapper for the NetHack Learning Environment (NLE) [1]. The wrapper replaces the non-language observations and actions with comparable language versions. The NLE offers a grand challenge for AI research while MiniHack [2] extends this potential to more specific and configurable tasks. By providing a language interface, we can enable further research on language agents and directly connect language models to a versatile environment. © 2023 The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See http://creativecommons.org/licenses/by/4.0/.
A practical guide to multi-objective reinforcement learning and planning
- Hayes, Conor, Rădulescu, Roxana, Bargiacchi, Eugenio, Källström, Johan, Macfarlane, Matthew, Reymond, Mathieu, Verstraeten, Timothy, Zintgraf, Luisa, Dazeley, Richard, Heintz, Frederick, Howley, Enda, Irissappane, Athirai, Mannion, Patrick, Nowé, Ann, Ramos, Gabriel, Restelli, Marcello, Vamplew, Peter, Roijers, Diederik
- Authors: Hayes, Conor , Rădulescu, Roxana , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederick , Howley, Enda , Irissappane, Athirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2022
- Type: Text , Journal article
- Relation: Autonomous Agents and Multi-Agent Systems Vol. 36, no. 1 (2022), p.
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems. © 2022, The Author(s).
- Authors: Hayes, Conor , Rădulescu, Roxana , Bargiacchi, Eugenio , Källström, Johan , Macfarlane, Matthew , Reymond, Mathieu , Verstraeten, Timothy , Zintgraf, Luisa , Dazeley, Richard , Heintz, Frederick , Howley, Enda , Irissappane, Athirai , Mannion, Patrick , Nowé, Ann , Ramos, Gabriel , Restelli, Marcello , Vamplew, Peter , Roijers, Diederik
- Date: 2022
- Type: Text , Journal article
- Relation: Autonomous Agents and Multi-Agent Systems Vol. 36, no. 1 (2022), p.
- Full Text:
- Reviewed:
- Description: Real-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems. © 2022, The Author(s).
A prioritized objective actor-critic method for deep reinforcement learning
- Nguyen, Ngoc, Nguyen, Thanh, Vamplew, Peter, Dazeley, Richard, Nahavandi, Saeid
- Authors: Nguyen, Ngoc , Nguyen, Thanh , Vamplew, Peter , Dazeley, Richard , Nahavandi, Saeid
- Date: 2021
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 33, no. 16 (2021), p. 10335-10349
- Full Text: false
- Reviewed:
- Description: An increasing number of complex problems have naturally posed significant challenges in decision-making theory and reinforcement learning practices. These problems often involve multiple conflicting reward signals that inherently cause agents’ poor exploration in seeking a specific goal. In extreme cases, the agent gets stuck in a sub-optimal solution and starts behaving harmfully. To overcome such obstacles, we introduce two actor-critic deep reinforcement learning methods, namely Multi-Critic Single Policy (MCSP) and Single Critic Multi-Policy (SCMP), which can adjust agent behaviors to efficiently achieve a designated goal by adopting a weighted-sum scalarization of different objective functions. In particular, MCSP creates a human-centric policy that corresponds to a predefined priority weight of different objectives. Whereas, SCMP is capable of generating a mixed policy based on a set of priority weights, i.e., the generated policy uses the knowledge of different policies (each policy corresponds to a priority weight) to dynamically prioritize objectives in real time. We examine our methods by using the Asynchronous Advantage Actor-Critic (A3C) algorithm to utilize the multithreading mechanism for dynamically balancing training intensity of different policies into a single network. Finally, simulation results show that MCSP and SCMP significantly outperform A3C with respect to the mean of total rewards in two complex problems: Food Collector and Seaquest. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature.
A survey of multi-objective sequential decision-making
- Roijers, Diederik, Vamplew, Peter, Whiteson, Shimon, Dazeley, Richard
- Authors: Roijers, Diederik , Vamplew, Peter , Whiteson, Shimon , Dazeley, Richard
- Date: 2013
- Type: Text , Journal article
- Relation: Journal of Artificial Intelligence Research Vol. 48, no. (2013), p. 67-113
- Full Text:
- Reviewed:
- Description: Sequential decision-making problems with multiple objectives arise naturally in practice and pose unique challenges for research in decision-theoretic planning and learning, which has largely focused on single-objective settings. This article surveys algorithms designed for sequential decision-making problems with multiple objectives. Though there is a growing body of literature on this subject, little of it makes explicit under what circumstances special methods are needed to solve multi-objective problems. Therefore, we identify three distinct scenarios in which converting such a problem to a single-objective one is impossible, infeasible, or undesirable. Furthermore, we propose a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function (which projects multi-objective values to scalar ones), and the type of policies considered. We show how these factors determine the nature of an optimal solution, which can be a single policy, a convex hull, or a Pareto front. Using this taxonomy, we survey the literature on multi-objective methods for planning and learning. Finally, we discuss key applications of such methods and outline opportunities for future work. © 2013 AI Access Foundation.
- Description: C1
- Authors: Roijers, Diederik , Vamplew, Peter , Whiteson, Shimon , Dazeley, Richard
- Date: 2013
- Type: Text , Journal article
- Relation: Journal of Artificial Intelligence Research Vol. 48, no. (2013), p. 67-113
- Full Text:
- Reviewed:
- Description: Sequential decision-making problems with multiple objectives arise naturally in practice and pose unique challenges for research in decision-theoretic planning and learning, which has largely focused on single-objective settings. This article surveys algorithms designed for sequential decision-making problems with multiple objectives. Though there is a growing body of literature on this subject, little of it makes explicit under what circumstances special methods are needed to solve multi-objective problems. Therefore, we identify three distinct scenarios in which converting such a problem to a single-objective one is impossible, infeasible, or undesirable. Furthermore, we propose a taxonomy that classifies multi-objective methods according to the applicable scenario, the nature of the scalarization function (which projects multi-objective values to scalar ones), and the type of policies considered. We show how these factors determine the nature of an optimal solution, which can be a single policy, a convex hull, or a Pareto front. Using this taxonomy, we survey the literature on multi-objective methods for planning and learning. Finally, we discuss key applications of such methods and outline opportunities for future work. © 2013 AI Access Foundation.
- Description: C1
AI apology : interactive multi-objective reinforcement learning for human-aligned AI
- Harland, Hadassah, Dazeley, Richard, Nakisa, Bahareh, Cruz, Francisco, Vamplew, Peter
- Authors: Harland, Hadassah , Dazeley, Richard , Nakisa, Bahareh , Cruz, Francisco , Vamplew, Peter
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 23 (2023), p. 16917-16930
- Full Text:
- Reviewed:
- Description: For an Artificially Intelligent (AI) system to maintain alignment between human desires and its behaviour, it is important that the AI account for human preferences. This paper proposes and empirically evaluates the first approach to aligning agent behaviour to human preference via an apologetic framework. In practice, an apology may consist of an acknowledgement, an explanation and an intention for the improvement of future behaviour. We propose that such an apology, provided in response to recognition of undesirable behaviour, is one way in which an AI agent may both be transparent and trustworthy to a human user. Furthermore, that behavioural adaptation as part of apology is a viable approach to correct against undesirable behaviours. The Act-Assess-Apologise framework potentially could address both the practical and social needs of a human user, to recognise and make reparations against prior undesirable behaviour and adjust for the future. Applied to a dual-auxiliary impact minimisation problem, the apologetic agent had a near perfect determination and apology provision accuracy in several non-trivial configurations. The agent subsequently demonstrated behaviour alignment with success that included up to complete avoidance of the impacts described by these objectives in some scenarios. © 2023, The Author(s).
- Authors: Harland, Hadassah , Dazeley, Richard , Nakisa, Bahareh , Cruz, Francisco , Vamplew, Peter
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 23 (2023), p. 16917-16930
- Full Text:
- Reviewed:
- Description: For an Artificially Intelligent (AI) system to maintain alignment between human desires and its behaviour, it is important that the AI account for human preferences. This paper proposes and empirically evaluates the first approach to aligning agent behaviour to human preference via an apologetic framework. In practice, an apology may consist of an acknowledgement, an explanation and an intention for the improvement of future behaviour. We propose that such an apology, provided in response to recognition of undesirable behaviour, is one way in which an AI agent may both be transparent and trustworthy to a human user. Furthermore, that behavioural adaptation as part of apology is a viable approach to correct against undesirable behaviours. The Act-Assess-Apologise framework potentially could address both the practical and social needs of a human user, to recognise and make reparations against prior undesirable behaviour and adjust for the future. Applied to a dual-auxiliary impact minimisation problem, the apologetic agent had a near perfect determination and apology provision accuracy in several non-trivial configurations. The agent subsequently demonstrated behaviour alignment with success that included up to complete avoidance of the impacts described by these objectives in some scenarios. © 2023, The Author(s).
An evaluation methodology for interactive reinforcement learning with simulated users
- Bignold, Adam, Cruz, Francisco, Dazeley, Richard, Vamplew, Peter, Foale, Cameron
- Authors: Bignold, Adam , Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2021
- Type: Text , Journal article
- Relation: Biomimetics Vol. 6, no. 1 (2021), p. 1-15
- Full Text:
- Reviewed:
- Description: Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
- Authors: Bignold, Adam , Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2021
- Type: Text , Journal article
- Relation: Biomimetics Vol. 6, no. 1 (2021), p. 1-15
- Full Text:
- Reviewed:
- Description: Interactive reinforcement learning methods utilise an external information source to evaluate decisions and accelerate learning. Previous work has shown that human advice could significantly improve learning agents’ performance. When evaluating reinforcement learning algorithms, it is common to repeat experiments as parameters are altered or to gain a sufficient sample size. In this regard, to require human interaction every time an experiment is restarted is undesirable, particularly when the expense in doing so can be considerable. Additionally, reusing the same people for the experiment introduces bias, as they will learn the behaviour of the agent and the dynamics of the environment. This paper presents a methodology for evaluating interactive reinforcement learning agents by employing simulated users. Simulated users allow human knowledge, bias, and interaction to be simulated. The use of simulated users allows the development and testing of reinforcement learning agents, and can provide indicative results of agent performance under defined human constraints. While simulated users are no replacement for actual humans, they do offer an affordable and fast alternative for evaluative assisted agents. We introduce a method for performing a preliminary evaluation utilising simulated users to show how performance changes depending on the type of user assisting the agent. Moreover, we describe how human interaction may be simulated, and present an experiment illustrating the applicability of simulating users in evaluating agent performance when assisted by different types of trainers. Experimental results show that the use of this methodology allows for greater insight into the performance of interactive reinforcement learning agents when advised by different users. The use of simulated users with varying characteristics allows for evaluation of the impact of those characteristics on the behaviour of the learning agent. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
Coarse Q-Learning : Addressing the convergence problem when quantizing continuous state variables
- Dazeley, Richard, Vamplew, Peter, Bignold, Adam
- Authors: Dazeley, Richard , Vamplew, Peter , Bignold, Adam
- Date: 2015
- Type: Text , Conference paper
- Relation: 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making
- Full Text: false
- Reviewed:
- Description: Value-based approaches to reinforcement learning (RL) maintain a value function that measures the long term utility of a state or state-action pair. A long standing issue in RL is how to create a finite representation in a continuous, and therefore infinite, state environment. The common approach is to use function approximators such as tile coding, memory or instance based methods. These provide some balance between generalisation, resolution, and storage, but converge slowly in multidimensional state environments. Another approach of quantizing state into lookup tables has been commonly regarded as highly problematic, due to large memory requirements and poor generalisation. In particular , attempting to reduce memory requirements and increase generalisation by using coarser quantization forms a non-Markovian system that does not converge. This paper investigates the problem in using quantized lookup tables and presents an extension to the Q-Learning algorithm, referred to as Coarse Q-Learning (C QL), which resolves these issues. The presented algorithm will be shown to drastically reduce the memory requirements and increase generalisation by simulating the Markov property. In particular, this algorithm means the size of the input space is determined by the granularity required by the policy being learnt, rather than by the inadequacies of the learning algorithm or the nature of the state-reward dynamics of the environment. Importantly, the method presented solves the problem represented by the curse of dimensionality.
Constructing stochastic mixture policies for episodic multiobjective reinforcement learning tasks
- Vamplew, Peter, Dazeley, Richard, Barker, Ewan, Kelarev, Andrei
- Authors: Vamplew, Peter , Dazeley, Richard , Barker, Ewan , Kelarev, Andrei
- Date: 2009
- Type: Text , Book chapter
- Relation: AI 2009 : Advances in Artificial Intelligence : 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009. Proceedings Chapter p. 340-349
- Full Text:
- Description: Multiobjective reinforcement learning algorithms extend reinforcement learning techniques to problems with multiple conflicting objectives. This paper discusses the advantages gained from applying stochastic policies to multiobjective tasks and examines a particular form of stochastic policy known as a mixture policy. Two methods are proposed for deriving mixture policies for episodic multiobjective tasks from deterministic base policies found via scalarised reinforcement learning. It is shown that these approaches are an efficient means of identifying solutions which offer a superior match to the user’s preferences than can be achieved by methods based strictly on deterministic policies.
- Description: 2003007906
- Authors: Vamplew, Peter , Dazeley, Richard , Barker, Ewan , Kelarev, Andrei
- Date: 2009
- Type: Text , Book chapter
- Relation: AI 2009 : Advances in Artificial Intelligence : 22nd Australasian Joint Conference, Melbourne, Australia, December 1-4, 2009. Proceedings Chapter p. 340-349
- Full Text:
- Description: Multiobjective reinforcement learning algorithms extend reinforcement learning techniques to problems with multiple conflicting objectives. This paper discusses the advantages gained from applying stochastic policies to multiobjective tasks and examines a particular form of stochastic policy known as a mixture policy. Two methods are proposed for deriving mixture policies for episodic multiobjective tasks from deterministic base policies found via scalarised reinforcement learning. It is shown that these approaches are an efficient means of identifying solutions which offer a superior match to the user’s preferences than can be achieved by methods based strictly on deterministic policies.
- Description: 2003007906
Discrete-to-deep reinforcement learning methods
- Kurniawan, Budi, Vamplew, Peter, Papasimeon, Michael, Dazeley, Richard, Foale, Cameron
- Authors: Kurniawan, Budi , Vamplew, Peter , Papasimeon, Michael , Dazeley, Richard , Foale, Cameron
- Date: 2022
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 34, no. 3 (2022), p. 1713-1733
- Full Text:
- Reviewed:
- Description: Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. In complex problems, a neural RL approach is often able to learn a better solution than tabular RL, but generally takes longer. This paper proposes two methods, Discrete-to-Deep Supervised Policy Learning (D2D-SPL) and Discrete-to-Deep Supervised Q-value Learning (D2D-SQL), whose objective is to acquire the generalisability of a neural network at a cost nearer to that of a tabular method. Both methods combine RL and supervised learning (SL) and are based on the idea that a fast-learning tabular method can generate off-policy data to accelerate learning in neural RL. D2D-SPL uses the data to train a classifier which is then used as a controller for the RL problem. D2D-SQL uses the data to initialise a neural network which is then allowed to continue learning using another RL method. We demonstrate the viability of our algorithms with Cartpole, Lunar Lander and an aircraft manoeuvring problem, three continuous-space environments with low-dimensional state variables. Both methods learn at least 38% faster than baseline methods and yield policies that outperform them. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
- Authors: Kurniawan, Budi , Vamplew, Peter , Papasimeon, Michael , Dazeley, Richard , Foale, Cameron
- Date: 2022
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 34, no. 3 (2022), p. 1713-1733
- Full Text:
- Reviewed:
- Description: Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. In complex problems, a neural RL approach is often able to learn a better solution than tabular RL, but generally takes longer. This paper proposes two methods, Discrete-to-Deep Supervised Policy Learning (D2D-SPL) and Discrete-to-Deep Supervised Q-value Learning (D2D-SQL), whose objective is to acquire the generalisability of a neural network at a cost nearer to that of a tabular method. Both methods combine RL and supervised learning (SL) and are based on the idea that a fast-learning tabular method can generate off-policy data to accelerate learning in neural RL. D2D-SPL uses the data to train a classifier which is then used as a controller for the RL problem. D2D-SQL uses the data to initialise a neural network which is then allowed to continue learning using another RL method. We demonstrate the viability of our algorithms with Cartpole, Lunar Lander and an aircraft manoeuvring problem, three continuous-space environments with low-dimensional state variables. Both methods learn at least 38% faster than baseline methods and yield policies that outperform them. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Elastic step DDPG : multi-step reinforcement learning for improved sample efficiency
- Ly, Adrian, Dazeley, Richard, Vamplew, Peter, Cruz, Francisco, Aryal, Sunil
- Authors: Ly, Adrian , Dazeley, Richard , Vamplew, Peter , Cruz, Francisco , Aryal, Sunil
- Date: 2023
- Type: Text , Conference paper
- Relation: 2023 International Joint Conference on Neural Networks, IJCNN 2023 Vol. 2023-June
- Full Text: false
- Reviewed:
- Description: A major challenge in deep reinforcement learning is that it requires more data to converge to an policy for complex problems. One way to improve sample efficiency is to use n-step updates to reduce the number of samples required to converge to a good policy. However n-step updates are known to be brittle and difficult to tune. Elastic Step DQN has shown that it is possible to automate the value of n in DQN to solve problems involving discrete action spaces, however the efficacy of the technique when applied on more complex problems and against problems with continuous action spaces is yet to be shown. In this paper we adapt the innovations proposed by Elastic Step DQN onto the DDPG algorithm and show empirically that Elastic Step DDPG is able to achieve a much stronger final training policy and is more sample efficient than DDPG. © 2023 IEEE.
Empirical evaluation methods for multiobjective reinforcement learning algorithms
- Vamplew, Peter, Dazeley, Richard, Berry, Adam, Issabekov, Rustam, Dekker, Evan
- Authors: Vamplew, Peter , Dazeley, Richard , Berry, Adam , Issabekov, Rustam , Dekker, Evan
- Date: 2011
- Type: Text , Journal article
- Relation: Machine Learning Vol. 84, no. 1-2 (2011), p. 51-80
- Full Text: false
- Reviewed:
- Description: While a number of algorithms for multiobjective reinforcement learning have been proposed, and a small number of applications developed, there has been very little rigorous empirical evaluation of the performance and limitations of these algorithms. This paper proposes standard methods for such empirical evaluation, to act as a foundation for future comparative studies. Two classes of multiobjective reinforcement learning algorithms are identified, and appropriate evaluation metrics and methodologies are proposed for each class. A suite of benchmark problems with known Pareto fronts is described, and future extensions and implementations of this benchmark suite are discussed. The utility of the proposed evaluation methods are demonstrated via an empirical comparison of two example learning algorithms. © 2010 The Author(s).
Evaluating human-like explanations for robot actions in reinforcement learning scenarios
- Cruz, Francisco, Young, Charlotte, Dazeley, Richard, Vamplew, Peter
- Authors: Cruz, Francisco , Young, Charlotte , Dazeley, Richard , Vamplew, Peter
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, 23-27 October 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vol. 2022-October, p. 894-901
- Full Text:
- Reviewed:
- Description: Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations. © 2022 IEEE.
- Authors: Cruz, Francisco , Young, Charlotte , Dazeley, Richard , Vamplew, Peter
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, 23-27 October 2022, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Vol. 2022-October, p. 894-901
- Full Text:
- Reviewed:
- Description: Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations. © 2022 IEEE.
Explainable reinforcement learning for broad-XAI: a conceptual framework and survey
- Dazeley, Richard, Vamplew, Peter, Cruz, Francisco
- Authors: Dazeley, Richard , Vamplew, Peter , Cruz, Francisco
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 23 (2023), p. 16893-16916
- Full Text:
- Reviewed:
- Description: Broad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent’s behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) aims to develop techniques to extract concepts from the agent’s: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. CXF is designed to incorporate many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes its decisions. This paper aims to: establish XRL as a distinct branch of XAI; introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper discusses how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI. © 2023, The Author(s).
- Authors: Dazeley, Richard , Vamplew, Peter , Cruz, Francisco
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 23 (2023), p. 16893-16916
- Full Text:
- Reviewed:
- Description: Broad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent’s behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) aims to develop techniques to extract concepts from the agent’s: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. CXF is designed to incorporate many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes its decisions. This paper aims to: establish XRL as a distinct branch of XAI; introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper discusses how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI. © 2023, The Author(s).
Explainable robotic systems : understanding goal-driven actions in a reinforcement learning scenario
- Cruz, Francisco, Dazeley, Richard, Vamplew, Peter, Moreira, Ithan
- Authors: Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Moreira, Ithan
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 25 (2023), p. 18113-18130
- Full Text:
- Reviewed:
- Description: Robotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot’s actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent’s observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson’s correlation and the mean squared error. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Explainable robotic systems : understanding goal-driven actions in a reinforcement learning scenario
- Authors: Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Moreira, Ithan
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 25 (2023), p. 18113-18130
- Full Text:
- Reviewed:
- Description: Robotic systems are more present in our society everyday. In human–robot environments, it is crucial that end-users may correctly understand their robotic team-partners, in order to collaboratively complete a task. To increase action understanding, users demand more explainability about the decisions by the robot in particular situations. Recently, explainable robotic systems have emerged as an alternative focused not only on completing a task satisfactorily, but also on justifying, in a human-like manner, the reasons that lead to making a decision. In reinforcement learning scenarios, a great effort has been focused on providing explanations using data-driven approaches, particularly from the visual input modality in deep learning-based systems. In this work, we focus rather on the decision-making process of reinforcement learning agents performing a task in a robotic scenario. Experimental results are obtained using 3 different set-ups, namely, a deterministic navigation task, a stochastic navigation task, and a continuous visual-based sorting object task. As a way to explain the goal-driven robot’s actions, we use the probability of success computed by three different proposed approaches: memory-based, learning-based, and introspection-based. The difference between these approaches is the amount of memory required to compute or estimate the probability of success as well as the kind of reinforcement learning representation where they could be used. In this regard, we use the memory-based approach as a baseline since it is obtained directly from the agent’s observations. When comparing the learning-based and the introspection-based approaches to this baseline, both are found to be suitable alternatives to compute the probability of success, obtaining high levels of similarity when compared using both the Pearson’s correlation and the mean squared error. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Human engagement providing evaluative and informative advice for interactive reinforcement learning
- Bignold, Adam, Cruz, Francisco, Dazeley, Richard, Vamplew, Peter, Foale, Cameron
- Authors: Bignold, Adam , Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 25 (2023), p. 18215-18230
- Full Text:
- Reviewed:
- Description: Interactive reinforcement learning proposes the use of externally sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has focused on the effect of human-sourced advice by including real-time feedback on the interactive reinforcement learning process, specifically aiming to improve the learning speed of the agent, while minimising the time demands on the human. This work focuses on answering which of two approaches, evaluative or informative, is the preferred instructional approach for humans. Moreover, this work presents an experimental setup for a human trial designed to compare the methods people use to deliver advice in terms of human engagement. The results obtained show that users giving informative advice to the learner agents provide more accurate advice, are willing to assist the learner agent for a longer time, and provide more advice per episode. Additionally, self-evaluation from participants using the informative approach has indicated that the agent’s ability to follow the advice is higher, and therefore, they feel their own advice to be of higher accuracy when compared to people providing evaluative advice. © 2022, The Author(s).
- Authors: Bignold, Adam , Cruz, Francisco , Dazeley, Richard , Vamplew, Peter , Foale, Cameron
- Date: 2023
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 35, no. 25 (2023), p. 18215-18230
- Full Text:
- Reviewed:
- Description: Interactive reinforcement learning proposes the use of externally sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has focused on the effect of human-sourced advice by including real-time feedback on the interactive reinforcement learning process, specifically aiming to improve the learning speed of the agent, while minimising the time demands on the human. This work focuses on answering which of two approaches, evaluative or informative, is the preferred instructional approach for humans. Moreover, this work presents an experimental setup for a human trial designed to compare the methods people use to deliver advice in terms of human engagement. The results obtained show that users giving informative advice to the learner agents provide more accurate advice, are willing to assist the learner agent for a longer time, and provide more advice per episode. Additionally, self-evaluation from participants using the informative approach has indicated that the agent’s ability to follow the advice is higher, and therefore, they feel their own advice to be of higher accuracy when compared to people providing evaluative advice. © 2022, The Author(s).
Human-aligned artificial intelligence is a multiobjective problem
- Vamplew, Peter, Dazeley, Richard, Foale, Cameron, Firmin, Sally, Mummery, Jane
- Authors: Vamplew, Peter , Dazeley, Richard , Foale, Cameron , Firmin, Sally , Mummery, Jane
- Date: 2018
- Type: Text , Journal article
- Relation: Ethics and Information Technology Vol. 20, no. 1 (2018), p. 27-40
- Full Text:
- Reviewed:
- Description: As the capabilities of artificial intelligence (AI) systems improve, it becomes important to constrain their actions to ensure their behaviour remains beneficial to humanity. A variety of ethical, legal and safety-based frameworks have been proposed as a basis for designing these constraints. Despite their variations, these frameworks share the common characteristic that decision-making must consider multiple potentially conflicting factors. We demonstrate that these alignment frameworks can be represented as utility functions, but that the widely used Maximum Expected Utility (MEU) paradigm provides insufficient support for such multiobjective decision-making. We show that a Multiobjective Maximum Expected Utility paradigm based on the combination of vector utilities and non-linear action–selection can overcome many of the issues which limit MEU’s effectiveness in implementing aligned AI. We examine existing approaches to multiobjective AI, and identify how these can contribute to the development of human-aligned intelligent agents. © 2017, Springer Science+Business Media B.V.
- Authors: Vamplew, Peter , Dazeley, Richard , Foale, Cameron , Firmin, Sally , Mummery, Jane
- Date: 2018
- Type: Text , Journal article
- Relation: Ethics and Information Technology Vol. 20, no. 1 (2018), p. 27-40
- Full Text:
- Reviewed:
- Description: As the capabilities of artificial intelligence (AI) systems improve, it becomes important to constrain their actions to ensure their behaviour remains beneficial to humanity. A variety of ethical, legal and safety-based frameworks have been proposed as a basis for designing these constraints. Despite their variations, these frameworks share the common characteristic that decision-making must consider multiple potentially conflicting factors. We demonstrate that these alignment frameworks can be represented as utility functions, but that the widely used Maximum Expected Utility (MEU) paradigm provides insufficient support for such multiobjective decision-making. We show that a Multiobjective Maximum Expected Utility paradigm based on the combination of vector utilities and non-linear action–selection can overcome many of the issues which limit MEU’s effectiveness in implementing aligned AI. We examine existing approaches to multiobjective AI, and identify how these can contribute to the development of human-aligned intelligent agents. © 2017, Springer Science+Business Media B.V.
Language representations for generalization in reinforcement learning
- Goodger, Nikolaj, Vamplew, Peter, Foale, Cameron, Dazeley, Richard
- Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
- Date: 2021
- Type: Text , Conference paper
- Relation: 13th Asian Conference on Machine Learning, Virtual, 17-19 November 2021, Proceedings of The 13th Asian Conference on Machine Learning Vol. 157, p. 390-405
- Full Text:
- Reviewed:
- Description: The choice of state and action representation in Reinforcement Learning (RL) has a significant effect on agent performance for the training task. But its relationship with generalization to new tasks is under-explored. One approach to improving generalization investigated here is the use of language as a representation. We compare vector-states and discreteactions to language representations. We find the agents using language representations generalize better and could solve tasks with more entities, new entities, and more complexity than seen in the training task. We attribute this to the compositionality of language
- Authors: Goodger, Nikolaj , Vamplew, Peter , Foale, Cameron , Dazeley, Richard
- Date: 2021
- Type: Text , Conference paper
- Relation: 13th Asian Conference on Machine Learning, Virtual, 17-19 November 2021, Proceedings of The 13th Asian Conference on Machine Learning Vol. 157, p. 390-405
- Full Text:
- Reviewed:
- Description: The choice of state and action representation in Reinforcement Learning (RL) has a significant effect on agent performance for the training task. But its relationship with generalization to new tasks is under-explored. One approach to improving generalization investigated here is the use of language as a representation. We compare vector-states and discreteactions to language representations. We find the agents using language representations generalize better and could solve tasks with more entities, new entities, and more complexity than seen in the training task. We attribute this to the compositionality of language