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.
@article{arxiv.2110.14538,
title = {Reinforcement Learning in Factored Action Spaces using Tensor Decompositions},
author = {Anuj Mahajan and Mikayel Samvelyan and Lei Mao and Viktor Makoviychuk and Animesh Garg and Jean Kossaifi and Shimon Whiteson and Yuke Zhu and Animashree Anandkumar},
journal= {arXiv preprint arXiv:2110.14538},
year = {2021}
}