- Title
- A multi-objective deep reinforcement learning framework
- Creator
- Nguyen, Thanh; Nguyen, Ngoc; Vamplew, Peter; Nahavandi, Saeid; Dazeley, Richard; Lim, Chee
- Date
- 2020
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/184658
- Identifier
- vital:16546
- Identifier
-
https://doi.org/10.1016/j.engappai.2020.103915
- Identifier
- ISBN:0952-1976 (ISSN)
- Abstract
- 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
- Publisher
- Elsevier Ltd
- Relation
- Engineering Applications of Artificial Intelligence Vol. 96, no. (2020), p.
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2020 Elsevier Ltd
- Rights
- Open Access
- Subject
- 40 Engineering; 46 Information and Computing SciencesDeep learning; Multi-objective; Multi-policy; Reinforcement learning; Single-policy
- Full Text
- Reviewed
- Hits: 1120
- Visitors: 1356
- Downloads: 409
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Accepted version | 1 MB | Adobe Acrobat PDF | View Details Download |