Co-Evolution As More Than a Scalable Alternative for Multi-Agent Reinforcement Learning

Patrick Grzywok

Keywords: reinforcement learning, multi-agent reinforcement learning, policy search, co-evolution, evolutionary algorithm

Abstract: In recent years, gradient based multi-agent reinforcement learning is growing in success. One contributing factor is the use of shared parameters for learning policy networks. While this approach scales well with the number of agents during execution it lacks this ambiguity for training as the number of produced samples grows linearly with the number of agents. For a very large number of agents, this could lead to an inefficient use of the circumstantial amount of produced samples. Moreover in single-agent reinforcement learning policy search with evolutionary algorithms showed viable success when sampling can be parallelized on a larger scale. The here proposed method does not only consider sampling in concurrent environments but further investigates sampling diverse parameters from the population in co-evolution in joint environments during training. This co-evolutionary policy search has shown to be capable of training a large number of agents. Beyond that, it has been shown to produce competitive results in smaller environments in comparison to gradient descent based methods. This surprising result make evolutionary algorithms a promising candidate for further research in the context of multi-agent reinforcement learning.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)

TL;DR: Evolutionary Algorithms can be competitively used for policy search in multi-agent reinforcement and can scale to a high number of agents.