Research map / Reinforcement learning / MDPs and planning
Robust Anytime Learning of Markov Decision Processes
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 LUI instead of UCRL2 for learning the uMDP | Chain Problem robust policy · Chain Problem | trajectories to recover optimal policy: $10^5$ -> 100 | Helped |
| Use uMDP-based robust policies (LUI, PAC, UCRL2) instead of MAP point estimates | Unfavourable Betting Game · Betting Game (win prob 0.2) | policy optimality: almost $10^4$ trajectories | Helped |
| Vary the prior strength intervals of LUI (ablation) | LUI · Grid environment | performance | No clear effect |
| Lower the bounds on the prior strength (ablation) | LUI · Chain with environment change | adaptation speed | Helped |
| Use randomized exploration (xi=0.8) instead of none (xi=1.0) (ablation) | Exploration policy · Chain environment change | performance after change | Helped |
| Use LUI instead of MAP/PAC/UCRL2 when environment changes | Chain Problem · Chain environment change | convergence to optimal policy before and after change | Helped |
Closest papers by meaning
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.93)
- Online MDP with Prototypes Information: A Robust Adaptive Approach (AAAI 2025 · similarity 0.93)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · similarity 0.91)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.90)
- Linear Mixture Distributionally Robust Markov Decision Processes (NeurIPS 2025 · similarity 0.90)
- Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel (ICML 2024 · similarity 0.89)
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.