Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
This work addresses the problem of developing robust multi-agent policies for AI researchers and practitioners, though it is incremental as it adapts existing actor-critic methods.
The paper tackled the challenge of applying deep reinforcement learning to multi-agent domains by addressing non-stationarity and high variance issues, resulting in an actor-critic adaptation that successfully learns complex coordination strategies in mixed cooperative-competitive environments.
We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies for each agent that leads to more robust multi-agent policies. We show the strength of our approach compared to existing methods in cooperative as well as competitive scenarios, where agent populations are able to discover various physical and informational coordination strategies.