Cooperation in Multi-Agent Reinforcement Learning with Proximal Policy Optimization

Music City Center 

In multi-agent reinforcement learning problems, the interaction of multiple decision-making agents in a shared environment can be modeled by a partially observable Markov game. It extends Markov Decision Processes to a multi-agent setting where agents have individual observations, actions, and rewards. In the multi-agent proximal policy optimization (MA-PPO) approach, the cooperation between the agents is investigated. We present a method to construct a deep stochastic policy that allows efficient optimization based on the actions of the agents. The effectiveness of the obtained statistical model is demonstrated by investigating the cooperation across multiple agents in an industrial application, in electric power distribution networks.

reinforcement learning

Markov decision process

proximal policy optimization

multi-agent

cooperation

electric power distribution networks 

Section on Statistical Learning and Data Science