Research map / Reinforcement learning / MDPs and planning
The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Matthieu Geist, Yuejie Chi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use total variation uncertainty set (robust MDP) instead of standard MDP | DRVI · TV-distance RMDP | sample complexity | Improved |
| tight analysis of DRVI for TV distance over full range of uncertainty level | DRVI · DRVI | sample complexity upper bound | Improved |
| use chi-square divergence uncertainty set instead of standard MDP | DRVI · chi-square RMDP | sample complexity | Mixed |
| new analysis of DRVI for chi-square set | DRVI · chi-square RMDP | dependence on state space size S | Improved |
| increase uncertainty level sigma toward 1 under TV distance | DRVI · TV-distance RMDP | sample complexity | Improved |
Closest papers by meaning
- Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms (NeurIPS 2024 · similarity 0.96)
- Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (NeurIPS 2024 · similarity 0.95)
- Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.93)
- Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation (NeurIPS 2026 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
