Research map / Reinforcement learning / Offline RL
Less Is More: Clustered Cross-Covariance Control for Offline RL
Nan Qiao, Sheng Yue, Shuning Wang, Yongheng Deng, Ju Ren
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 C4 instead of best baseline TSRL | TSRL · MuJoCo locomotion (10k samples) | normalized score: 57.2 -> 75.7 | Improved |
| use C4 instead of best baseline BPPO | BPPO · Adroit (10k samples) | normalized score: 23.1 -> 21.6 | Hurt |
| use C4 instead of TSRL | TSRL · AntMaze (10k samples) | normalized score: 22.0 -> 27.0 | Improved |
| use C4 instead of BPPO | BPPO · Maze2D (10k samples) | normalized score: 120.6 -> 126.9 | Improved |
| use C4 instead of TSRL on Halfcheetah-expert | TSRL · Halfcheetah-expert (10k) | normalized score: 42.0 -> 75.8 | Improved |
| use C4 instead of BPPO on Walker2d-medium-expert | BPPO · Walker2d-medium-expert (10k) | normalized score: 61.3 -> 96.3 | Improved |
| use C4 instead of TSRL on Hopper-medium-expert | TSRL · Hopper-medium-expert (10k) | normalized score: 56.6 -> 81.3 | Improved |
| add C4 regularizer to CQL or TD3+BC versus LN and DR3 | CQL and TD3+BC · MuJoCo locomotion (10k samples) | normalized score | Improved |
| vary regularization strength lambda and base coefficient alpha (ablation) | C4 · MuJoCo locomotion | normalized score | No clear effect |
| vary number of initial clusters and data quality/coverage (ablation) | C4 · MuJoCo locomotion | normalized score | No clear effect |
Closest papers by meaning
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression (NeurIPS 2024 · similarity 0.88)
- Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization (AAAI 2024 · similarity 0.88)
- Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL (NeurIPS 2023 · similarity 0.88)
- Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning (ICLR 2024 · similarity 0.88)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 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.
