Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
Abstract
We present an extended abstract for the previously published work TESSERACT [Mahajan et al., 2021], which proposes a novel solution for Reinforcement Learning (RL) in large, factored action spaces using tensor decompositions. The goal of this abstract is twofold: (1) To garner greater interest amongst the tensor research community for creating methods and analysis for approximate RL, (2) To elucidate the generalised setting of factored action spaces where tensor decompositions can be used. We use cooperative multi-agent reinforcement learning scenario as the exemplary setting where the action space is naturally factored across agents and learning becomes intractable without resorting to approximation on the underlying hypothesis space for candidate solutions.
Additional Information
Attribution 4.0 International (CC BY 4.0)Attached Files
Accepted Version - 2110.14538.pdf
Files
2110.14538.pdf
Additional details
Identifiers
- Eprint ID
- 115607
- Resolver ID
- CaltechAUTHORS:20220714-224657047
Related works
- Describes
- 10.48550/arXiv.2110.14538 (DOI)
- https://tensorworkshop.github.io/NeurIPS2021/index.html (URL)
Dates
- Created
-
2022-07-15Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field