RoboMimic

Robomimic is a dataset/benchmark that contains challenging robotic manipulation tasks used to evaluate the performance of reinforcement learning policies.

Papers using RoboMimic (12)

MODIP: Efficient Model-Based Optimization for Diffusion Policies2026Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning2026XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies2026Aligning Flow Map Policies with Optimal Q-Guidance2026World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry2026Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation2026Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?2025Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning2025IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning2025M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model2024Reinforcement Learning with Generalizable Gaussian Splatting2024 · 4 citesOn-Robot Reinforcement Learning with Goal-Contrastive Rewards2024