Research map / Reinforcement learning / Visual and representation RL
CATAL: Causally Disentangled Task Representation Learning for Offline Meta-Reinforcement Learning
Shan Cong, Chao Yu, Xiangyuan Lan
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 CATAL's causal disentanglement components (independence, consistency, remapping) to the base COMRL framework (ablation) | CATAL · Hopper (ID) | average return: 243.6 -> 289.9 | Improved |
| add CATAL's three components to the base framework (ablation) | CATAL · Walker (OOD) | average return: 150.3 -> 256.3 | Improved |
| add the consistency constraint (ablation) | CATAL · Half-Cheetah (OOD) | average return: -213.5 -> -184.2 | Improved |
| add the independence constraint (ablation) | CATAL · Half-Cheetah (OOD) | average return: -251.5 -> -184.2 | Improved |
| add the independence constraint (ablation) | CATAL · Hopper (ID) | average return: 196.6 -> 289.9 | Improved |
| replace CORRO with CATAL representations | BRAC meta-policy · Ant (OOD) | average return: 136.4 -> 164.7 | Improved |
| replace CSRO with CATAL representations | BRAC meta-policy · Walker (OOD) | average return: 230.3 -> 256.3 | Improved |
Closest papers by meaning
- Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations (AAAI 2024 · similarity 0.91)
- Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning (ICLR 2025 · similarity 0.91)
- Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning (AAAI 2025 · similarity 0.91)
- Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement (NeurIPS 2024 · similarity 0.89)
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.
