Research map / Reinforcement learning / Visual and representation RL
Cross-Domain Policy Adaptation via Value-Guided Data Filtering
Kang Xu, Chenjia Bai, Xiaoteng Ma, Dong Wang, Bin Zhao, Zhen Wang, Xuelong Li, Wei Li
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 |
|---|---|---|---|
| increase source-to-target data ratio Gamma from 5 to 20 (ablation) | VGDF · MuJoCo dynamics-shift environments | return | Improved |
| select source data with ratio at most 50% instead of using all source data (Mix) (ablation) | VGDF · morphology-shift environments | return | Improved |
| use all source data without selection (Mix) (ablation) | VGDF · kinematic-shift environments | return | No clear effect |
| add optimistic exploration policy (ablation) | VGDF · MuJoCo environments | sample efficiency | Improved |
| VGDF + BC instead of H2O in offline source setting | H2O · offline source online target, six tasks | return: 5761 -> 4834 | Mixed |
| VGDF + BC instead of symmetric sampling | Symmetric sampling · walker - no right thigh | return: 872 -> 3293 | Improved |
| Finetune baseline versus VGDF | VGDF · eight MuJoCo environments | return | Mixed |
Closest papers by meaning
- Cross-Domain Policy Adaptation by Capturing Representation Mismatch (ICML 2024 · similarity 0.92)
- Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Horizon Adaptive Offline Policy Learning via Value Stitching (NeurIPS 2026 · similarity 0.88)
- In-Context Policy Adaptation via Cross-Domain Skill Diffusion (AAAI 2025 · similarity 0.88)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · 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.
