Bayesian Actor-Critic Algorithms

Bayesian Actor-Critic Algorithms
Mohammad Ghavamzadeh - University of Alberta, Canada Yaakov Engel - University of Alberta, Canada
We1 present a new actor-critic learning model in which a Bayesian class of non-parametric critics, using Gaussian process temporal difference learning is used. Such critics model the state-action value function as a Gaussian process, allowing Bayes' rule to be used in computing the posterior distribution over state-action value functions, conditioned on the observed data. Appropriate choices of the prior covariance (kernel) between stateaction values and of the parametrization of the policy allow us to obtain closed-form expressions for the posterior distribution of the gradient of the average discounted return with respect to the policy parameters. The posterior mean, which serves as our estimate of the policy gradient, is used to update the policy, while the posterior covariance allows us to gauge the reliability of the update.

Mohammad Ghavamzadeh - University of Alberta, Canada
Yaakov Engel - University of Alberta, Canada

We1 present a new actor-critic learning model in which a Bayesian class of non-parametric critics, using Gaussian process temporal difference learning is used. Such critics model the state-action value function as a Gaussian process, allowing Bayes' rule to be used in computing the posterior distribution over state-action value functions, conditioned on the observed data. Appropriate choices of the prior covariance (kernel) between stateaction values and of the parametrization of the policy allow us to obtain closed-form expressions for the posterior distribution of the gradient of the average discounted return with respect to the policy parameters. The posterior mean, which serves as our estimate of the policy gradient, is used to update the policy, while the posterior covariance allows us to gauge the reliability of the update.