Research map / Reinforcement learning / Offline RL
Improving Zero-Shot Offline RL via Behavioral Task Sampling
Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud
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 |
|---|---|---|---|
| replace uniform hypersphere task sampling with Behavioral Task Distribution (GMM over dataset-derived task vectors) | SF and FB zero-shot RL (AEnc, Trans, LRA-P, LRA-SR, BYOL, BYOL-gamma, FB) · ExORL Cheetah, Walker, Quadruped | zero-shot test performance: average +20%; better in 13 of 15 tests, comparable in 2 | Improved |
| use BTD-sampling with FB | Forward-Backward representation · Cheetah, Walker, Quadruped | zero-shot test performance | Improved |
| use BTD-sampling instead of uniform sampling | all baseline methods · Cheetah, Walker, Quadruped | variance across representation methods | Improved |
| increase latent task dimension from 50 to 1000 with uniform sampling (ablation) | baseline uniform task sampling · Cheetah, Walker, Quadruped | test performance | Hurt |
| increase latent task dimension from 50 to 1000 with BTD-sampling (ablation) | BTD-sampling · Cheetah, Walker, Quadruped | test performance | No clear effect |
| mix uniform sampled tasks into BTD-sampling (interpolation alpha from 0 to 1) (ablation) | BTD-sampling · Cheetah, Walker, Quadruped | test performance | Hurt |
| mix uniform tasks into BTD-sampling (ablation) | BTD-sampling · Quadruped | test performance | No clear effect |
Closest papers by meaning
- Zero-Shot Reinforcement Learning from Low Quality Data (NeurIPS 2024 · similarity 0.93)
- Zero-Shot Reinforcement Learning via Function Encoders (ICML 2024 · similarity 0.91)
- Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings (ICML 2024 · similarity 0.91)
- Provable Zero-Shot Generalization in Offline Reinforcement Learning (ICML 2025 · similarity 0.90)
- Towards Robust Zero-Shot Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Foundation Policies with Hilbert Representations (ICML 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.
