Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning

Shariq Iqbal, Christian Schroeder de Witt, Bei Peng, Wendelin Boehmer, Shimon Whiteson, Fei Sha

Keywords: MARL, multi-agent reinforcement learning, value function factorization, attention

Abstract: Real world multi-agent tasks often involve varying types and quantities of agents and non-agent entities; however, agents within these tasks rarely need to consider all others at all times in order to act effectively. Factored value function approaches have historically leveraged such independences to improve learning efficiency, but these approaches typically rely on domain knowledge to select fixed subsets of state features to include in each factor. We propose to utilize value function factoring with random subsets of entities in each factor as an auxiliary objective in order to disentangle value predictions from irrelevant entities. This factoring approach is instantiated through a simple attention mechanism masking procedure. We hypothesize that such an approach helps agents learn more effectively in multi-agent settings by discovering common trajectories across episodes within sub-groups of agents/entities. Our approach, Randomized Entity-wise Factorization for Imagined Learning (REFIL), outperforms all strong baselines by a significant margin in challenging StarCraft micromanagement tasks.

One-sentence Summary: We propose an auxiliary objective to disentangle value function predictions from irrelevant entities in cooperative MARL and find that it significantly improves performance in settings with varying quantities and types of agents.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=aq1LzEhRc-