Multi-Agent Trust Region Policy Optimization
–arXiv.org Artificial Intelligence
We extend trust region policy optimization (TRPO) to multi-agent reinforcement learning (MARL) problems. We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. By making a series of approximations to the consensus optimization model, we propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO). This algorithm can optimize distributed policies based on local observations and private rewards. The agents do not need to know observations, rewards, policies or value/action-value functions of other agents. The agents only share a likelihood ratio with their neighbors during the training process. The algorithm is fully decentralized and privacy-preserving. Our experiments on two cooperative games demonstrate its robust performance on complicated MARL tasks.
arXiv.org Artificial Intelligence
Oct-18-2020
- Country:
- North America > United States
- Rhode Island (0.04)
- New York > New York County
- New York City (0.04)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.04)
- Europe
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report (1.00)
- Industry:
- Information Technology > Security & Privacy (0.93)
- Technology: