Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
This addresses exploration challenges for multi-agent systems in sparse-reward environments, with incremental improvements over existing methods.
The paper tackled the problem of exploration in sparse-reward multi-agent reinforcement learning by proposing SEAC, a method that shares experience among agents, resulting in learning in fewer steps and achieving higher returns compared to baselines and state-of-the-art algorithms.
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. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms two baselines and two 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.