Research map / Reinforcement learning / MDPs and planning
Best-Effort Policies for Robust Markov Decision Processes
Alessandro Abate, Thom Badings, Giuseppe De Giacomo, Francesco Fabiano
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 |
|---|---|---|---|
| add a second value-iteration pass under best-case transition probabilities as tie-breaker | PRISM robust value iteration on interval MDPs · slippery gridworld IMDP, nu=0.0 | best-effort actions [%]: 21.9 -> 100.0 | Improved |
| add best-case tie-breaker pass | PRISM robust value iteration · slippery gridworld IMDP, |S|=10000 | runtime [s]: 48.9 -> 54.4 | Mixed |
| add best-case tie-breaker pass | PRISM robust value iteration · slippery gridworld IMDP, |S|=100 | runtime [s]: 2.0 -> 3.9 | Hurt |
| add best-case tie-breaker pass to robust value iteration | RVI on s-rectangular RMDPs · slippery gridworld RMDP, |S|=100, nu=0.0 | best-effort actions [%]: 0.0 -> 100.0 | Improved |
| add derivative-based tie-breaker to robust value iteration | RVI on s-rectangular RMDPs · slippery gridworld RMDP, |S|=100, nu=0.5 | best-effort actions [%]: 49.2 -> 100.0 | Improved |
| add derivative-based tie-breaker to robust value iteration | RVI on s-rectangular RMDPs · slippery gridworld RMDP, |S|=900 | runtime [s]: 163.6 -> 172.0 | No clear effect |
| add best-case tie-breaker to robust value iteration | RVI on s-rectangular RMDPs · slippery gridworld RMDP, |S|=900 | runtime [s]: 163.6 -> 274.4 | Hurt |
| vary order in which best-effort action is defined (nu) (ablation) | PRISM robust value iteration · slippery gridworld IMDP, |S|=100 | best-effort actions [%]: 21.9 -> 89.9 | Improved |
Closest papers by meaning
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.91)
- Efficient Value Iteration for s-rectangular Robust Markov Decision Processes (ICML 2024 · similarity 0.91)
- Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization (AAAI 2024 · similarity 0.90)
- Revisiting Subgradient Dominance in Robust MDPs: Counterexamples, Hardness, and Sufficient Conditions (NeurIPS 2026 · similarity 0.90)
- A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes (ICML 2024 · similarity 0.89)
- Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity (ICML 2025 · 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.
