Explicit Explore-Exploit Algorithms in Continuous State Spaces

Henaff, Mikael

arXiv.org Artificial Intelligence 

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models consistent with current experience and explores by finding policies which induce high disagreement between their state predictions. It then exploits using the refined set of models or experience gathered during exploration. We show that under realizability and optimal planning assumptions, our algorithm provably finds a near-optimal policy with a number of samples that is polynomial in a structural complexity measure which we show to be low in several natural settings. We then give a practical approximation using neural networks and demonstrate its performance and sample efficiency in practice.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found