Research map / Learning theory and algorithms / Prediction and decision losses
Risk-Aware Stochastic Shortest Path
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 value iteration instead of linear programming for CVaR-SSP | CVaR-SSP · Grid (x=8) | runtime: 199s -> 2s | Helped |
| Use value iteration instead of linear programming for CVaR-SSP | CVaR-SSP · Grid (x=16) | runtime: 2,373s -> 11s | Helped |
| Use value iteration instead of linear programming for CVaR-SSP | CVaR-SSP · Grid (x=32) | runtime: >$1h -> 221s | Helped |
| Use value iteration instead of linear programming for CVaR-SSP | CVaR-SSP · FireWire | runtime: MO -> 3s | Helped |
| Use value iteration instead of linear programming for CVaR-SSP | CVaR-SSP · WLAN | runtime: MO -> 1s | Helped |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · Grid (x=4), threshold 10% | objective value: 6.7 expected total cost; 11.0 CVaR | Mixed |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · Grid (x=8), threshold 10% | objective value: 13.1 expected total cost; 17.6 CVaR | Mixed |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · Grid (x=16), threshold 10% | objective value: 19.3 expected total cost; 23.6 CVaR | Mixed |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · Grid (x=32), threshold 10% | objective value: 35.9 expected total cost; 40.8 CVaR | Mixed |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · FireWire, threshold 10% | objective value: 166.2 expected total cost; 167.0 CVaR | Mixed |
| Optimize tail risk with CVaR rather than expected total cost | SSP control · WLAN, threshold 10% | objective value: 48.0 expected total cost; 62.3 CVaR | Mixed |
Closest papers by meaning
- Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret (NeurIPS 2021 · similarity 0.89)
- Planning and Learning in Average Risk-aware MDPs (NeurIPS 2025 · similarity 0.87)
- Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees (NeurIPS 2026 · similarity 0.86)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · similarity 0.86)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.86)
- Approximate Bilevel Difference Convex Programming for Bayesian Risk Markov Decision Processes (AAAI 2025 · 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.