Coordinated Proximal Policy Optimization
This work addresses multi-agent coordination challenges in reinforcement learning, offering an incremental improvement over existing methods like PPO and MAPPO.
The paper tackles the problem of multi-agent reinforcement learning by extending Proximal Policy Optimization (PPO) to a coordinated version called CoPPO, which adapts step sizes among agents to reduce variance and achieve dynamic credit assignment, resulting in competitive performance with strong baselines like MAPPO in tasks such as cooperative matrix games and StarCraft II micromanagement.
We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monotonicity of policy improvement when optimizing a theoretically-grounded joint objective, and derive a simplified optimization objective based on a set of approximations. We then interpret that such an objective in CoPPO can achieve dynamic credit assignment among agents, thereby alleviating the high variance issue during the concurrent update of agent policies. Finally, we demonstrate that CoPPO outperforms several strong baselines and is competitive with the latest multi-agent PPO method (i.e. MAPPO) under typical multi-agent settings, including cooperative matrix games and the StarCraft II micromanagement tasks.