Research map / Reinforcement learning / MDPs and planning
Querying to Find a Safe Policy under Uncertain Safety Constraints in Markov Decision Processes
Shun Zhang, Edmund Durfee, Satinder Singh
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 |
|---|---|---|---|
| select queries with set-cover heuristic hSC instead of most-likely-policy | query selection · Example 2 | expected queries: 2.24 -> 1.7 | Improved |
| use hICR instead of hSC when safe policies are unlikely | query selection · Example 6 | expected queries: 2.71 -> 2.09 | Improved |
| use hSC or hICR instead of exact optimal query policy | query selection · 6x6 navigation, 14 carpets | computation time per query: 41.41 ± 6.59 sec for optimal | Improved |
| use hICR instead of hSC | query selection · 6x6 navigation, varying carpets | queries to resolve | Improved |
| use single-objective hSC-IIS or hSC-rel instead of combined hSC (ablation) | query selection · 6x6 navigation, varying pF | queries to resolve | Mixed |
| use probability-maximization instead of hSC | query selection · 6x6 navigation, varying pF | queries to resolve | Hurt |
Closest papers by meaning
- Probabilistic Shielding for Safe Reinforcement Learning (AAAI 2025 · similarity 0.86)
- SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP (ICML 2024 · similarity 0.86)
- Flipping-based Policy for Chance-Constrained Markov Decision Processes (NeurIPS 2024 · similarity 0.86)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.85)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.85)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.85)
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.
