Research map / Reinforcement learning / MDPs and planning
Point-Based Methods for Model Checking in Partially Observable 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 SARSOP point-based planning instead of Lovejoy belief-space discretization | Quantitative POMDP model checking · 3×3 PO Grid World | time to reach a given precision | Helped |
| Use quantitative satisfaction-probability optimization rather than requiring probability-1 satisfaction | POMDP policy synthesis for LTL objectives · Rock Sample | ability to return a policy | Helped |
| Maintain belief over both environment and automaton state instead of assuming end components are observed | POMDP LTL model checking · POMDPs with unobservable labels | policy synthesis under partial observability | Helped |
| Use SARSOP on the product POMDP and translate its value bounds into satisfaction-probability bounds | POMDP model checker · LTL satisfaction | bound on success probability | Helped |
| Scale the drone surveillance domain from [5,5] to [7,7] | POMDP model checker (SARSOP) · Drone Surveillance (U) | solving time: 78.3 -> 12587.5 | Hurt |
Closest papers by meaning
- Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives (AAAI 2025 · similarity 0.90)
- Belief-State Query Policies for User-Aligned POMDPs (NeurIPS 2024 · similarity 0.89)
- Multi-Environment POMDPs with Finite-Horizon Objectives (NeurIPS 2026 · similarity 0.89)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.88)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.87)
- Scalable Policy-Based RL Algorithms for POMDPs (NeurIPS 2025 · similarity 0.86)
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.