Develops stochastic first-order methods for robust policy evaluation and approximate policy iteration in continuous-state robust MDPs, achieving 'O(1/ε^{2}) sample complexity for both evaluation and optimization.
Faster last-iterate convergence of policy optimiza- tion in zero-sum Markov games.arXiv preprint arXiv:2210.01050, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Markov Decision Processes on Continuous State Spaces
Develops stochastic first-order methods for robust policy evaluation and approximate policy iteration in continuous-state robust MDPs, achieving 'O(1/ε^{2}) sample complexity for both evaluation and optimization.