Research map / Reinforcement learning / Offline RL
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Shenzhi Wang, Qisen Yang, Jiawei Gao, Matthieu Gaetan Lin, HAO CHEN, Liwei Wu, Ning Jia, Shiji Song, Gao Huang
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 FamO2O state-adaptive balance to IQL | IQL · D4RL Locomotion total | normalized score: 718.3 -> 772.0 | Improved |
| add FamO2O to IQL | IQL · D4RL AntMaze total | normalized score: 428.7 -> 478.3 | Improved |
| add FamO2O to AWAC | AWAC · D4RL Locomotion total | normalized score: 648.4 -> 714.9 | Improved |
| add FamO2O to AWAC | AWAC · D4RL AntMaze total | normalized score: 124.7 -> 243.7 | Improved |
| add FamO2O to AWAC | AWAC · antmaze-medium-play | normalized score: 0.0 -> 34.2 | Improved |
| add FamO2O to IQL | IQL · antmaze-umaze-diverse | normalized score: 37.8 -> 70.8 | Improved |
| add FamO2O to AWAC | AWAC · hopper-medium-expert | normalized score: 97.7 -> 92.9 | Hurt |
| add FamO2O to IQL | IQL · halfcheetah-medium-replay | normalized score: 53.7 -> 53.1 | No clear effect |
| add FamO2O to AWAC and IQL on medium datasets with consistent data quality | AWAC/IQL · hopper, halfcheetah, walker2d medium | normalized score: 65.4 -> 90.7 | Improved |
| replace balance model with random balance coefficient selector (ablation) | FamO2O · D4RL Locomotion total | normalized score: 771.96 -> 730.70 | Hurt |
| replace balance model with random selector (ablation) | FamO2O · hopper-medium-replay | normalized score: 97.64 -> 80.87 | Hurt |
| replace balance model with random selector (ablation) | FamO2O · halfcheetah-medium-replay | normalized score: 53.07 -> 53.75 | No clear effect |
Closest papers by meaning
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization (ICLR 2024 · similarity 0.90)
- Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.90)
- Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL (ICML 2025 · 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.
