Research map / Reinforcement learning / MDPs and planning
Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 generative-model samples and solve for a Nash equilibrium against an adversarial perturbation | RMDP policy learning · Toy two-layer RMDP under worst-case perturbations | robust policy success | Helped |
| Train only for the optimal policy in the training MDP, without accounting for perturbations | Toy two-layer RMDP · Worst-case perturbations | robust policy error | Hurt |
| Use online RQ-learning or RSARSA rather than generative-model sampling | Toy two-layer RMDP · Worst-case perturbations | robust policy error | Hurt |
| Account for perturbation risk with a robust policy | RMDP policy learning · Toy two-layer RMDP under random perturbations | expected reward | Helped |
| Use a small TVDC radius, u≤ ε/(16H^2) | Pair-wise NE solver · TVDC RMDP | samples per state-action pair for Err(π̂*) ≤ ε | Helped |
Closest papers by meaning
- Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (NeurIPS 2024 · similarity 0.91)
- Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty (ICML 2024 · similarity 0.90)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.89)
- Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization (ICML 2025 · similarity 0.89)
- Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms (NeurIPS 2024 · similarity 0.89)
- Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.88)
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.