Timezone: »

Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
Filippos Christianos · Lukas Schäfer · Stefano Albrecht

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1504

Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called shared Experience Actor-Critic(SEAC), applies experience sharing in an actor-critic framework by combining the gradients of different agents. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms several baselines and state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, experience sharing makes the difference between learning to solve the task and not learning at all.

Author Information

Filippos Christianos (University of Edinburgh)
Lukas Schäfer (University of Edinburgh)
Stefano Albrecht (University of Edinburgh)

More from the Same Authors