Reinforcement Learning in Factored Action Spaces using Tensor Decompositions
arXiv:2110.14538
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.
References in corpus (12)
- Tensor Decomposition for Signal Processing and Machine Learning
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Counterfactual Multi-Agent Policy Gradients
- Tensor Methods in Computer Vision and Deep Learning
- Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning
- MAVEN: Multi-Agent Variational Exploration
- Open-Ended Learning Leads to Generally Capable Agents
- The Sample-Complexity of General Reinforcement Learning
- Reinforcement Learning in Rich-Observation MDPs using Spectral Methods
- Symmetry Learning for Function Approximation in Reinforcement Learning
- UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
- Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning