Research map / Reinforcement learning / Policy gradient and actor-critic
Towards Robust Off-Policy Learning for Runtime Uncertainty
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 DR instead of the greedy nIPS workaround | Off-policy robustness evaluation · Glass | prediction fluctuation: α=0.2: 0.0333 vs 0.0173; α=0.4: 0.1081 vs 0.0667; α=0.6: 0.1896 vs 0.157 | Helped |
| Use DR instead of the greedy nIPS workaround | Off-policy robustness evaluation · Ecoli | prediction fluctuation: α=0.2: 0.0634 vs 0.0427; α=0.4: 0.0883 vs 0.0635; α=0.6: 0.1077 vs 0.0757 | Helped |
| Use DR instead of the greedy nIPS workaround | Off-policy robustness evaluation · SatImage | prediction fluctuation: α=0.2: 0.0762 vs 0.0681; α=0.4: 0.1049 vs 0.0754; α=0.6: 0.1215 vs 0.0823 | Helped |
| Increase the uncertainty degree α | Proposed minimax off-policy optimization · Simulation datasets | oracle value during training | Mixed |
| Use robust rather than standard off-policy learning | E-commerce recommendation experiment · Real-world testing data | policy outcome | Helped |
Closest papers by meaning
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.89)
- Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation (ICML 2025 · similarity 0.88)
- Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.88)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Dynamic Uncertainty Estimation for Offline Reinforcement Learning (AAAI 2025 · similarity 0.88)
- SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning (AAAI 2025 · 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.