An actor critic algorithm based on Grassmanian search

We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are known a priori, however, only an unknown subset of them could be relevant. The policy parameters that correspond to an observed target policy are recovered using 1-regularized logistic regression that best fits the observed state-action samples. We establish bounds on the difference between the average reward of the estimated and the original policy (regret) in terms of the generalization error and the ergodic coefficient of the underlying Markov chain. To that end, we combine sample complexity theory and sensitivity analysis of the stationary distribution of Markov chains. Our analysis suggests that to achieve regret within order O( √ ), it suffices to use training sample size on the order of Ω(log n · poly(1/ )), where n is the number of the features. We demonstrate the effectiveness of our method on a synthetic robot navigation example.

show abstract

Learning Policies for Markov Decision Processes From Data

Hanawal

Líu

Zhu

et al. 2019

IEEE Trans. Automat. Contr.

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

An actor critic algorithm based on Grassmanian search

Cited by 1 publication

References 11 publications

Learning Policies for Markov Decision Processes From Data

Learning Policies for Markov Decision Processes From Data

Contact Info

Product

Resources

About