Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$ -realizable MDPs

27 October 2022

Papers citing "Confident Approximate Policy Iteration for Efficient Local Planning in $q^π$-realizable MDPs"

4 / 4 papers shown

Title
Offline RL via Feature-Occupancy Gradient Ascent Gergely Neu Nneka Okolo OffRL 29 0 0 22 May 2024
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice Toshinori Kitamura Tadashi Kozuno Yunhao Tang Nino Vieillard Michal Valko ... Olivier Pietquin M. Geist Csaba Szepesvári Wataru Kumagai Yutaka Matsuo OffRL 30 2 0 22 May 2023
Sample Efficient Deep Reinforcement Learning via Local Planning Dong Yin S. Thiagarajan N. Lazić Nived Rajaraman Botao Hao Csaba Szepesvári 20 4 0 29 Jan 2023
Approximation Benefits of Policy Gradient Methods with Aggregated States Daniel Russo 38 7 0 22 Jul 2020