Research map / Reinforcement learning / Offline RL
Percentile Criterion Optimization in Offline Reinforcement Learning
Cyrus Cousins, Elita Lobo, Marek Petrik, Yair Zick
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 |
|---|---|---|---|
| Use VaR instead of the strongest listed baseline, WBCR l1 | Robust policy learning · Riverswim | robust performance: 68.54 $\pm$ 5.08 vs 67.9 $\pm$ 3.82 | Improved |
| Use VaR instead of Soft-Robust | Robust policy learning · Inventory | robust performance: 457.95 $\pm$ 0.74 vs 460.6 $\pm$ 0.0 | Hurt |
| Use VaR instead of Soft-Robust | Robust policy learning · Population-Small | robust performance: -3102.48 $\pm$ 429.7 vs -3647.18 $\pm$ 94.62 | Improved |
| Use VaRN instead of VaR, assuming a multivariate-normal transition posterior (ablation) | VaR framework · Riverswim | robust performance: 68.54 $\pm$ 5.08 -> 67.27 $\pm$ 0.0 | Hurt |
| Use VaRN instead of VaR, assuming a multivariate-normal transition posterior (ablation) | VaR framework · Inventory | robust performance: 457.95 $\pm$ 0.74 -> 452.78 $\pm$ 0.02 | Hurt |
| Use VaRN instead of VaR, assuming a multivariate-normal transition posterior (ablation) | VaR framework · Population-Small | robust performance: -3102.48 $\pm$ 429.7 -> -4005.53 $\pm$ 8.76 | Hurt |
| Use VaRN instead of VaR, assuming a multivariate-normal transition posterior (ablation) | VaR framework · Population | robust performance: -4576.87 $\pm$ 147.3 -> -4570.17 $\pm$ 38.84 | Improved |
Closest papers by meaning
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.88)
- Dynamic Uncertainty Estimation for Offline Reinforcement Learning (AAAI 2025 · similarity 0.87)
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.87)
- Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.87)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.87)
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.
