Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
UCB EXPLORATION VIA Q-ENSEMBLES
Richard Y. Chen, Szymon Sidor, Pieter Abbeel, John Schulman
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experiments show significant gains on the Atari benchmark.
TL;DR:Adapting UCB exploration to ensemble Q-learning improves over prior methods such as Double DQN, A3C+ on Atari benchmark