- Title
- Language representations for generalization in reinforcement learning
- Creator
- Goodger, Nikolaj; Vamplew, Peter; Foale, Cameron; Dazeley, Richard
- Date
- 2021
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/188074
- Identifier
- vital:17201
- Abstract
- 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
- Publisher
- ACML
- 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
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- https://creativecommons.org/licenses/by/4.0/
- Rights
- Copyright © The authors and PMLR 2022
- Rights
- Open Access
- Subject
- Reinforcement learning; Generalization; Representation selection
- Full Text
- Reviewed
- Hits: 925
- Visitors: 819
- Downloads: 57
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Published version | 4 MB | Adobe Acrobat PDF | View Details Download |