Research map / Reinforcement learning / MDPs and planning
Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity
Laixi Shi, 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 |
|---|---|---|---|
| add pessimism (LCB penalty) to distributionally robust value iteration (ablation) | DRVI-LCB vs DRVI · Gambler's problem, small sample (N=100) | sub-optimality value gap | Improved |
| add pessimism (LCB penalty) to distributionally robust value iteration (ablation) | DRVI-LCB vs DRVI · Gambler's problem, varying N (100 to 5000) | sub-optimality gap | Improved |
| add pessimism (LCB penalty) to distributionally robust value iteration (ablation) | DRVI-LCB vs DRVI · Gambler's problem, growing number of states S | value gap | Improved |
| add pessimism (LCB penalty) to distributionally robust value iteration (ablation) | DRVI-LCB vs DRVI · Gambler's problem, trajectory data (K trajectories) | sub-optimality value gap | Improved |
| train with distributional robustness (sigma 0.01 or 0.2) instead of the non-robust optimal policy (ablation) | DRVI-LCB policy, N=1000 · Gambler's problem, perturbed p_head in [0.25,0.75] | ratio of winning | Improved |
Closest papers by meaning
- Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (NeurIPS 2024 · similarity 0.94)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.93)
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.92)
- Dynamic Uncertainty Estimation for Offline Reinforcement Learning (AAAI 2025 · similarity 0.92)
- Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction (ICML 2025 · similarity 0.92)
- Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.92)
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.
