Research map / Reinforcement learning / Offline RL
Critic Regularized Regression
Ziyu Wang, Alexander Novikov, Konrad Zolna, Josh S Merel, Jost Tobias Springenberg, Scott E Reed, Bobak Shahriari, Noah Siegel, Caglar Gulcehre, Nicolas Heess, Nando de Freitas
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 |
|---|---|---|---|
| CRR exp vs ABM | offline RL · Humanoid Run | episode return: 302 -> 586 | Improved |
| CRR exp vs ABM | offline RL · Humanoid Corridor | episode return: 64 -> 918 | Improved |
| CRR vs ABM | offline RL · Rodent Mazes | episode return: 478 -> 459 | Hurt |
| CRR binary vs D4PG | offline RL · Manipulator Insert Ball | episode return: 154 -> 654 | Improved |
| advantage-filtered regression (CRR exp) vs plain BC (ablation) | same network · Humanoid Corridor | episode return: 220 -> 918 | Improved |
| binary filter instead of exp weighting (ablation) | CRR · Cartpole Swingup | episode return: 664 -> 860 | Improved |
| binary filter instead of exp weighting (ablation) | CRR · Humanoid Run | episode return: 586 -> 412 | Hurt |
| binary max (A_max) instead of binary (A_mean) (ablation) | CRR binary · Humanoid Run | episode return: 412 -> 226 | Hurt |
| binary max (A_max) instead of binary (A_mean) (ablation) | CRR binary · Finger Turn Hard | episode return: 755 -> 833 | Improved |
| critic-weighted policy (CWP) action selection (ablation) | CRR · DCS/locomotion selected envs | episode return | Improved |
| turn off Gaussian noise at evaluation (ablation) | CRR · low/moderate action-dim envs | episode return | Mixed |
Closest papers by meaning
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.92)
- Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL (ICML 2024 · similarity 0.91)
- Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset (ICLR 2025 · similarity 0.90)
- Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL (ICML 2025 · similarity 0.90)
- Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees (ICLR 2024 · similarity 0.90)
- A Clean Slate for Offline Reinforcement Learning (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.
