Bayesian Curiosity for Efficient Exploration in Reinforcement Learning [article]

Tom Blau, Lionel Ott, Fabio Ramos
2019 arXiv   pre-print
Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like ϵ-greedy. This contributes to the problem of high sample complexity, as the algorithm wastes effort by repeatedly visiting parts of the state space that have already been explored. We introduce a novel method based on Bayesian linear regression and latent space embedding to generate an intrinsic reward signal that encourages the
more » ... ng agent to seek out unexplored parts of the state space. This method is computationally efficient, simple to implement, and can extend any state-of-the-art reinforcement learning algorithm. We evaluate the method on a range of algorithms and challenging control tasks, on both simulated and physical robots, demonstrating how the proposed method can significantly improve sample complexity.
arXiv:1911.08701v1 fatcat:yj5dcs45bvf57n56j5mkytqpnm