PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning
This addresses a limitation in multi-agent reinforcement learning for partially observable environments, offering an incremental improvement over existing methods.
The paper tackled the problem of significant estimation error in partially observable multi-agent reinforcement learning due to constraints from agents' action orderings, and proposed PAC, a framework using counterfactual predictions to assist value factorization, which achieved improved results over state-of-the-art algorithms on predator-prey and StarCraft II benchmarks.
Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods. It allows optimizing a joint action-value function through the maximization of factorized per-agent utilities due to monotonicity. In this paper, we show that in partially observable MARL problems, an agent's ordering over its own actions could impose concurrent constraints (across different states) on the representable function class, causing significant estimation error during training. We tackle this limitation and propose PAC, a new framework leveraging Assistive information generated from Counterfactual Predictions of optimal joint action selection, which enable explicit assistance to value function factorization through a novel counterfactual loss. A variational inference-based information encoding method is developed to collect and encode the counterfactual predictions from an estimated baseline. To enable decentralized execution, we also derive factorized per-agent policies inspired by a maximum-entropy MARL framework. We evaluate the proposed PAC on multi-agent predator-prey and a set of StarCraft II micromanagement tasks. Empirical results demonstrate improved results of PAC over state-of-the-art value-based and policy-based multi-agent reinforcement learning algorithms on all benchmarks.