Research map / Reinforcement learning / Offline RL
Unsupervised Behavior Extraction via Random Intent Priors
Hao Hu, Yiqin Yang, Jianing Ye, Ziqing Mai, Chongjie Zhang
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 random intent priors instead of behavior cloning to extract offline behaviors | UBER policy reuse · Antmaze medium-play, 100k steps | normalized score: 0.0±0.0 -> 91.9±2.9 | Improved |
| Use random intent priors instead of behavior cloning to extract offline behaviors | UBER policy reuse · Antmaze large-play, 100k steps | normalized score: 0.0±0.0 -> 62.8±2.6 | Improved |
| Use random intent priors instead of average-reward offline behavior extraction (ablation) | UBER · Mujoco downstream tasks | online performance | Improved |
| Use policy expansion (PEX) rather than critic-guided policy reuse (CUP) (ablation) | UBER · Downstream tasks | online performance | Improved |
| Use random intent priors rather than behavior cloning | Behavior extraction from reward-free offline data · Return-distribution entropy across D4RL tasks | return-distribution entropy: DATASET: 1.21, 1.47, 0.86, 0.71, 1.97, 0.82; UBER: 2.01, 1.92, 2.69, 2.45, 2.32, 1.11 | Improved |
| Use random intent priors rather than behavior cloning | Behavior extraction from reward-free offline data · Antmaze medium, large | online performance | Improved |
Closest papers by meaning
- How to Leverage Unlabeled Data in Offline Reinforcement Learning (ICML 2022 · similarity 0.88)
- Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration (ICML 2025 · similarity 0.88)
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.88)
- DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation (ICML 2024 · similarity 0.87)
- Reasoning with Latent Diffusion in Offline Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Information-Theoretic Reward Decomposition for Generalizable RLHF (NeurIPS 2025 · similarity 0.86)
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.
