Research map / Reinforcement learning / MDPs and planning
RAO*: An Algorithm for Chance-Constrained POMDP's
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 |
|---|---|---|---|
| model chance constraint as CC-POMDP (exact execution risk) instead of unit-cost C-POMDP (ablation) | RAO* · PSR example instance | execution cost: 53.330 -> 36.509 | Helped |
| model chance constraint as CC-POMDP instead of unit-cost C-POMDP (ablation) | RAO* · SA example instance | utility: 29.454 -> 29.454 | No clear effect |
| add 4 sensors (12 -> 16) to the power network (ablation) | RAO* · PSR single faults, Delta=1 | runtime (s): 2.256 -> 0.165 | Helped |
| add 4 sensors (12 -> 16) to the power network (ablation) | RAO* · PSR single faults, Delta=1 | cost: 30.54 -> 22.89 | Helped |
| relax risk bound Delta from 0.5 to 1.0 (no chance constraint) (ablation) | RAO* · PSR single faults, 12 sensors | runtime (s): 0.059 -> 2.256 | Hurt |
| relax risk bound Delta from 0.5 to 1.0 (ablation) | RAO* · PSR single faults, 12 sensors | cost: 44.18 -> 30.54 | Helped |
| increase risk bound Delta from 0.002 to 0.01 (SA, window 40) (ablation) | RAO* · SA window 40s | utility: 21.958 -> 29.433 | Helped |
| increase risk bound Delta from 0.01 to 0.05 (SA, window 100) (ablation) | RAO* · SA window 100s | utility: 29.454 -> 29.454 | No clear effect |
Closest papers by meaning
- Multi-Environment POMDPs with Finite-Horizon Objectives (NeurIPS 2026 · similarity 0.86)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.86)
- Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives (AAAI 2025 · similarity 0.85)
- Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability (NeurIPS 2025 · similarity 0.85)
- Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees (NeurIPS 2026 · similarity 0.85)
- Belief-State Query Policies for User-Aligned POMDPs (NeurIPS 2024 · similarity 0.84)
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.