UCB EXPLORATION VIA Q-ENSEMBLES

Richard Y. Chen, Szymon Sidor, Pieter Abbeel, John Schulman

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

Keywords: Reinforcement learning, Q-learning, ensemble method, upper confidence bound

Data: [Arcade Learning Environment](https://paperswithcode.com/dataset/arcade-learning-environment)