facebookresearch / modemv2
MoDem-V2 combines the sample efficiency of the original MoDem with conservative exploration in order to quickly and safely learn manipulation skills on real robots.
☆13Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for modemv2
- PWM: Policy Learning with Large World Models☆37Updated 3 months ago
- (ICLR 2024) Reverse Forward Curriculum Learning☆38Updated 2 months ago
- ☆14Updated last year
- [RA-L 2024] Novel action spaces leveraging redundancy in 7 DoF arms enable efficient & precise learning in robotic manipulation☆16Updated 5 months ago
- ☆28Updated last year
- Connect agent policies for distributed ML applications☆16Updated last month
- Collection of MuJoCo robotics environments equipped with both vision and tactile sensing☆41Updated 4 months ago
- ☆52Updated last year
- Official PyTorch implementation of "Entity-Centric Reinforcement Learning for Object Manipulation from Pixels", Haramati et al., ICLR 202…☆22Updated 7 months ago
- ☆28Updated last year
- ☆43Updated 2 months ago
- ☆22Updated 3 years ago
- Coarse-to-fine Q-Network☆33Updated 3 months ago
- ☆27Updated 3 months ago
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆51Updated last year
- Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation (2023)☆28Updated last year
- Models implemented on the Dexterous Arm☆26Updated 2 years ago
- Code release for "Training Robots to Evaluate Robots" (CoRL'22, Best Paper Award)☆18Updated last year
- ☆14Updated last year
- Code for "DittoGym: Learning to Control Soft Shape-Shifting Robots" by Suning Huang, Boyuan Chen, Huazhe Xu, and Vincent Sitzmann.☆26Updated 6 months ago
- ☆14Updated 7 months ago
- Code for SAPG: Split and Aggregate Policy Gradients (ICML 2024)☆43Updated 2 months ago
- [NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning the…☆60Updated 3 months ago
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆40Updated this week
- From Imitation to Refinement -- Residual RL for Precise Visual Assembly☆55Updated last week
- Distilling Diffusion Policy into consistency models☆18Updated 9 months ago
- Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation☆62Updated last year
- KitchenShift: Evaluating Zero-Shot Generalization of Imitation-Based Policy Learning Under Domain Shifts☆15Updated 2 years ago
- Official implementation of Get a Grip: Multi-Finger Grasp Evaluation at Scale Enables Robust Sim-to-Real Transfer☆13Updated this week
- Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation (BUDS)☆44Updated 2 years ago