Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes
Author:
Top Cited Papers
- 28 April 2022
- journal article
- research article
- Published by Springer Nature in Mathematical Programming
- Vol. 198 (1) , 1059-1106
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- National Science Foundation (1953199)
- National Institute of Food and Agriculture (2020-67021-31526)
- National Science Foundation (1909298)
This publication has 9 references indexed in Scilit:
- Finite-Sample Analysis of Two-Time-Scale Natural Actor–Critic AlgorithmIEEE Transactions on Automatic Control, 2022
- Statistical estimation of ergodic Markov chain kernel over discrete state spaceBernoulli, 2021
- Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPsProceedings of the AAAI Conference on Artificial Intelligence, 2020
- First-order and Stochastic Optimization Methods for Machine Learning2020
- On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operatorsComputational Optimization and Applications, 2014
- Online Markov Decision ProcessesMathematics of Operations Research, 2009
- Robust Stochastic Approximation Approach to Stochastic ProgrammingSIAM Journal on Optimization, 2009
- Markov Decision Processes1994
- Functional Approximations and Dynamic ProgrammingMathematical Tables and Other Aids to Computation, 1959