Resource

 

Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning

Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
G. Papoudakis, F. Christianos, A. Rahman, S. Albrecht
Intermediate
Peer Reviewed Paper
Theory

From the abstract

Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which has received increasing attention is multi-agent reinforcement learning, in which multiple agents learn concurrently to coordi- nate their actions. In such multi-agent environments, additional learning problems arise due to the contin- ually changing decision-making policies of agents. This paper surveys recent works that address the non-stationarity problem in multi-agent deep rein- forcement learning. The surveyed methods range from modifications in the training procedure, such as centralized training, to learning representations of the opponent’s policy, meta-learning, commu- nication, and decentralized learning. The survey concludes with a list of open problems and possible lines of future research.

 

 

This resource is included in the following topics and journeys: