Augmented Bayesian Policy Search

TL;DR

This paper introduces Augmented Bayesian Search (ABS), a novel method that combines Bayesian Optimization with policy gradients to improve deterministic policy search in reinforcement learning, especially for high-dimensional locomotion tasks.

Contribution

The paper proposes a new mean function for Bayesian Optimization that incorporates the action-value function, bridging BO and policy gradient methods for scalable reinforcement learning.

Findings

ABS performs competitively on high-dimensional locomotion tasks.

The method effectively combines the advantages of BO and policy gradients.

Experimental results show improved exploration and policy quality.

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 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 probabilistic model. 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.