Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning

Understand

Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently.

• This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings.
• Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents.
• In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing with partially shared critic.