Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning
This work addresses scalability issues in cooperative multi-agent reinforcement learning, which is important for applications like robotics and game AI, though it appears incremental as it builds directly on existing MADDPG methods.
The paper tackles the scalability problem of multi-agent deep deterministic policy gradient (MADDPG) in cooperative settings by proposing parameter sharing variants, achieving faster learning and better memory efficiency while scaling effectively with increasing numbers of agents.
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. Benchmarks from rllab show that the proposed method has advantages in learning speed and memory efficiency, well scales with growing amount of agents, and moreover, it can make full use of reward sharing and exchangeability if possible.