facebookresearch / vip
Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"
☆136Updated last year
Related projects ⓘ
Alternatives and complementary repositories for vip
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆86Updated last year
- ☆24Updated 6 months ago
- ☆125Updated 8 months ago
- A Benchmark for Evaluating Generalization for Robotic Manipulation☆70Updated 3 months ago
- Hierarchical Universal Language Conditioned Policies☆66Updated 8 months ago
- ☆58Updated last month
- ☆52Updated last year
- ☆80Updated 5 months ago
- PyTorch implementation of the Hiveformer research paper☆47Updated last year
- ☆27Updated 3 months ago
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆62Updated 5 months ago
- From Imitation to Refinement -- Residual RL for Precise Visual Assembly☆53Updated last week
- Masked World Models for Visual Control☆118Updated last year
- Demo-Driven Mobile Bi-Manual Manipulation Benchmark.☆108Updated last month
- FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)☆142Updated this week
- Official Implementation of RoboCLIP (NeurIPS 2023)☆35Updated 3 months ago
- [CVPR 2024] Hierarchical Diffusion Policy for Multi-Task Robotic Manipulation☆132Updated 7 months ago
- ☆39Updated last year
- Masked Visual Pre-training for Robotics☆218Updated last year
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆23Updated 10 months ago
- ☆90Updated last year
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆109Updated last year
- Code for https://jangirrishabh.github.io/lookcloser/☆30Updated last year
- Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation (2023)☆28Updated last year
- ☆69Updated 2 years ago
- Code for Reinforcement Learning from Vision Language Foundation Model Feedback☆55Updated 5 months ago
- Code for BAKU: An Efficient Transformer for Multi-Task Policy Learning☆75Updated 4 months ago
- [CoRL 2023] XSkill: cross embodiment skill discovery☆50Updated 7 months ago
- Q-attention (within the ARM system) and coarse-to-fine Q-attention (within C2F-ARM system).☆165Updated 8 months ago
- The repository for a thorough empirical evaluation of pre-trained vision model performance across different downstream policy learning me…☆22Updated last year