Research map / Multi-agent systems and games / Human-AI and goal-conditioned
RoboHive: A Unified Framework for Robot Learning
Vikash Kumar, Rutav Shah, Gaoyue Zhou, Vincent Moens, Vittorio Caggiano, Abhishek Gupta, Aravind Rajeswaran
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 visual observations to state observations | RoboHive environments · Arm Manipulation | samples per second: 7473 -> 993 | Hurt |
| add visual observations to state observations | RoboHive environments · Hand manipulation | samples per second: 8785 -> 1713 | Hurt |
| add visual observations to state observations | RoboHive environments · Multi-task | samples per second: 4430 -> 346 | Hurt |
| use pixel (v2d) observations instead of state | FrankaReachRandom · Arm Manipulation | samples per second: 8911.4261 -> 1055.2824 | Hurt |
| use pixel (v2d) observations instead of state | relocate · Hand manipulation | samples per second: 9317.9963 -> 1737.4508 | Hurt |
| use visual representation baselines (RRL, R3M, VC1) instead of privileged state policy | behavior cloning · Kitchen, Adroit and D'Kitty datasets | task performance | Hurt |
| use visual representations instead of proprioception-only input | behavior cloning · D'Kitty locomotion (ROBEL) | task performance | Hurt |
| train on human teleoperated data instead of expert policy data | visual baselines · Kitchen suite | task performance | Hurt |
Closest papers by meaning
- ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning (CVPR 2025 · similarity 0.87)
- RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete (CVPR 2025 · similarity 0.86)
- RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models (NeurIPS 2026 · similarity 0.86)
- RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation (ICML 2024 · similarity 0.86)
- RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation (ICLR 2025 · similarity 0.86)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 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.
