papers AI Learner
The Github is limit! Click to go to the new site.

Object Exchangeability in Reinforcement Learning: Extended Abstract

2019-05-07
John Mern, Dorsa Sadigh, Mykel Kochenderfer

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.02698

PDF

https://arxiv.org/pdf/1905.02698


Similar Posts

Comments