Timezone: »

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Ryan Lowe · YI WU · Aviv Tamar · Jean Harb · OpenAI Pieter Abbeel · Igor Mordatch

Wed Dec 06 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #205

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.

Author Information

Ryan Lowe (McGill University)
YI WU (UC Berkeley)
Aviv Tamar (UC Berkeley)
Jean Harb (McGill University)
OpenAI Pieter Abbeel (OpenAI, UC Berkeley)
Igor Mordatch (OpenAI)

More from the Same Authors