Augmented Bayesian Policy Search

Mahdi Kallel, Debabrota Basu, Riad Akrour, Carlo D'Eramo

Keywords: Reinforcement learning, Policy search, Bayesian optimization, Gaussian Processes

TL;DR: A novel mean function for Gaussian processes that bridges the gap between reinforcement learning and Bayesian optimization (BO) by leveraging the performance difference lemma to augment BO schemes with an action-value function.

Abstract:

Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement and interpret. However, in practice, exploration is largely performed by stochastic policies.
First-order Bayesian Optimization (BO) methods offer a principled way of performing exploration using deterministic policies. This is done through a learned probabilistic model, in the form of a Gaussian Process (GP), of the objective function and its gradient. Nonetheless, such approaches treat policy search as a black-box problem, and thus, neglect the reinforcement learning nature of the problem. In this work, we leverage the performance difference lemma to introduce a novel mean function for the GP. This results in augmenting BO methods with the action-value function. Hence, we call our method Augmented Bayesian Search (ABS). Interestingly, this new mean function enhances the posterior gradient with the deterministic policy gradient, effectively bridging the gap between BO and policy gradient methods. The resulting algorithm combines the convenience of the direct policy search with the scalability of reinforcement learning. We validate ABS on high-dimensional locomotion problems and demonstrate competitive performance compared to existing direct policy search schemes.

Already Accepted Paper At Another Venue: already accepted somewhere else

Submission Number: 20