Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
This work addresses the challenge of intractable learning in factored action spaces for multi-agent reinforcement learning, though it is incremental as it extends prior published work.
The paper tackles the problem of reinforcement learning in large, factored action spaces by proposing a novel solution using tensor decompositions, specifically in cooperative multi-agent scenarios where the action space is factored across agents, making learning intractable without approximations.
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.