Research map / Reinforcement learning / Offline RL
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
Yevgen Chebotar, Karol Hausman, Yao Lu, Ted Xiao, Dmitry Kalashnikov, Jacob Varley, Alex Irpan, Benjamin Eysenbach, Ryan C Julian, Chelsea Finn, Sergey Levine
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 goal chaining to Actionable Models (ablation) | Actionable Models · Real-world container placing | success rate: 8% to 66% | Improved |
| pre-train on offline goal-reaching data before task-reward fine-tuning | Real-world instance grasping · Grasp box | success rate: 0% -> 27% | Improved |
| pre-train on offline goal-reaching data before task-reward fine-tuning | Real-world instance grasping · Grasp banana | success rate: 4% -> 20% | Improved |
| pre-train on offline goal-reaching data before task-reward fine-tuning | Real-world instance grasping · Grasp milk | success rate: 1% -> 20% | Improved |
| remove conservative regularization for unseen actions (ablation) | offline goal-conditioned Q-learning · Simulated visual goal reaching | success rate | Hurt |
| replace contrastive unseen-action negatives with random goal negatives | offline goal-conditioned Q-learning · Simulated visual goal reaching | success rate | Hurt |
| remove goal chaining (ablation) | Actionable Models · Simulated fixture placing | success rate | Hurt |
| use goal-conditioned pre-training | QT-Opt online learning · Simulated instance grasping | training speed | Improved |
| add a 10% auxiliary goal-reaching objective | QT-Opt online learning · Simulated instance grasping | training speed | Improved |
| use goal-conditioned behavioral cloning instead of Actionable Models | offline simulated visual goal reaching · simulated manipulation tasks | success rate | Hurt |
Closest papers by meaning
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.88)
- Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning (ICML 2025 · similarity 0.88)
- GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation (AAAI 2024 · similarity 0.88)
- Reasoning with Latent Diffusion in Offline Reinforcement Learning (ICLR 2024 · similarity 0.88)
- Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data (ICLR 2024 · similarity 0.87)
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models (NeurIPS 2025 · 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.
