Back to Search
Start Over
Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
- Publication Year :
- 2023
-
Abstract
- Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance difference lemma that characterizes the landscape of multi-agent policy optimization, we find that the localized action value function serves as an ideal descent direction for each local policy. Motivated by the observation, we present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate. We extend our algorithm to the off-policy setting and introduce pessimism to policy evaluation, which aligns with experiments. To our knowledge, this is the first provably convergent multi-agent PPO algorithm in cooperative Markov games.<br />Comment: ICML 2023
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2305.04819
- Document Type :
- Working Paper