Object Exchangeability in Reinforcement Learning: Extended Abstract
Abstract
Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches.
Cite
@article{arxiv.1905.02698,
title = {Object Exchangeability in Reinforcement Learning: Extended Abstract},
author = {John Mern and Dorsa Sadigh and Mykel Kochenderfer},
journal= {arXiv preprint arXiv:1905.02698},
year = {2019}
}
Comments
In Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), Montreal,Canada, May 13 to 17, 2019,IFAAMAS, 3 pages