Research map / Reinforcement learning / Offline RL
EXPO: Stable Reinforcement Learning with Expressive Policies
Perry Dong, Qiyang Li, Dorsa Sadigh, Chelsea Finn
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 value-maximizing actions in the TD backup (not only for sampling) (ablation) | EXPO · Robomimic Can and Square | sample efficiency and success | Improved |
| add Gaussian action edits on top of base policy samples (ablation) | EXPO · pen-binary-v0 | normalized return | Improved |
| add Gaussian action edits on top of base policy samples (ablation) | EXPO · Robomimic Square | success rate | Improved |
| use better offline data (higher imitation-learning success) (ablation) | EXPO · Robomimic Square (subsampled demos) | success at 1M steps | Improved |
| add entropy backup with soft sampling for narrow datasets (ablation) | EXPO · Square with weak offline data | success rate | Improved |
| drop the offline dataset after pretraining, warm-start with pretrained policy rollouts (ablation) | EXPO · Robomimic Lift and Can | sample efficiency | No clear effect |
| vary number of action samples N and edit scale beta (ablation) | EXPO · Robomimic Lift and Square | performance | Mixed |
| fine-tune with EXPO versus offline-RL baselines with expressive policies (IDQL, DAC, QSM, DIPO) | diffusion policy · 12 sparse-reward tasks | sample efficiency: 2-3x | Improved |
Closest papers by meaning
- Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning (ICLR 2026 · similarity 0.91)
- Q-Flow: Stable and Expressive Reinforcement Learning with Flow-based Policy (ICML 2026 · similarity 0.91)
- Flow-Based Policy for Online Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Is Value Learning Really the Main Bottleneck in Offline RL? (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.
