Research map / Reinforcement learning / MDPs and planning
Corruption-Robust Offline Reinforcement Learning with General Function Approximation
Chenlu Ye, Rui Yang, Quanquan Gu, Tong Zhang
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 uncertainty weighting to MSG (ablation) | MSG · 12 corrupted D4RL-style tasks (average) | average return: 1083.6 -> 2212.8 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Halfcheetah adversarial dynamics | average return: -87.3 -> 4144.3 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Halfcheetah random reward | average return: 4339.5 -> 7299.9 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Halfcheetah random dynamics | average return: 212.9 -> 1425.0 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Walker2d random reward | average return: 539.1 -> 2189.7 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Walker2d random dynamics | average return: 2122.8 -> 2278.9 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Walker2d adversarial reward | average return: 605.8 -> 1433.4 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Hopper random reward | average return: 1599.6 -> 2021.1 | Improved |
| add uncertainty weighting to MSG (ablation) | MSG · Hopper adversarial dynamics | average return: 717.7 -> 931.2 | Improved |
| use UWMSG instead of SAC-N under random reward corruption | UWMSG · Halfcheetah random reward | average return: 7357.5 -> 7299.9 | No clear effect |
| use UWMSG instead of EDAC under adversarial dynamics | UWMSG · Halfcheetah adversarial dynamics | average return: 374.0 -> 4144.3 | Improved |
| use UWMSG instead of SAC-N on Hopper adversarial reward | UWMSG · Hopper adversarial reward | average return: 111.8 -> 751.4 | Improved |
Closest papers by meaning
- Towards Robust Offline Reinforcement Learning under Diverse Data Corruption (ICLR 2024 · similarity 0.93)
- Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption (ICML 2024 · similarity 0.92)
- Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption (AAAI 2024 · similarity 0.92)
- Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling (ICLR 2025 · similarity 0.91)
- Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions (NeurIPS 2024 · similarity 0.90)
- Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption (NeurIPS 2025 · similarity 0.90)
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.
