Bayesian policy gradient and actor-critic algorithms

Abstract

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which tend to have high variance, requiring many samples and resulting in slow convergence. We first propose a Bayesian framework for policy gradient, based on modeling the policy gradient as a Gaussian process. This reduces the number of samples needed to obtain accurate gradient estimates. Moreover, estimates of the natural gradient and a measure of the uncertainty in the gradient estimates, namely, the gradient covariance, are provided at little extra cost. Since the proposed framework considers system trajectories as its basic observable unit, it does not require the dynamics within trajectories to be of any particular form, and can be extended to partially observable problems. On the downside, it cannot exploit the Markov property when the system is Markovian. To address this, we supplement our Bayesian policy gradient framework with a new actor-critic learning model in which a Bayesian class of non-parametric critics, based on Gaussian process temporal difference learning, is used. Such critics model the action-value function as a Gaussian process, allowing Bayes rule to be used to compute the posterior distribution over action-value functions, conditioned on the observed data. Appropriate choices of the policy parameterization and of the prior covariance (kernel) between action-values yield closed-form expressions for the posterior of the gradient of the expected return with respect to the policy parameters. We perform detailed experimental comparisons of the proposed Bayesian policy gradient and actor-critic algorithms with classic Monte-Carlo based policy gradient methods, on a number of reinforcement learning problems.

Published in Journal of Machine Learning Research 17(66):1-53, 2016

References in corpus (8)

• Analysis of Thompson Sampling for the multi-armed bandit problem
• Thompson Sampling for Contextual Bandits with Linear Payoffs
• Further Optimal Regret Bounds for Thompson Sampling
• Model-Based Bayesian Exploration
• The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
• A Bayesian Sampling Approach to Exploration in Reinforcement Learning
• Experiments with Infinite-Horizon, Policy-Gradient Estimation
• On the Prior Sensitivity of Thompson Sampling

Cited by in corpus (6)

• Bayesian Reinforcement Learning: A Survey
• Soft-Robust Actor-Critic Policy-Gradient
• Bayesian Policy Gradients via Alpha Divergence Dropout Inference
• Kalman meets Bellman: Improving Policy Evaluation through Value Tracking
• Reinforcement Learning Ship Autopilot: Sample efficient and Model Predictive Control-based Approach
• Epistemic Risk-Sensitive Reinforcement Learning