facebookresearch / vipLinks
Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"
☆179Updated 2 years ago
Alternatives and similar repositories for vip
Users that are interested in vip are comparing it to the libraries listed below
Sorting:
- Hierarchical Universal Language Conditioned Policies☆77Updated last year
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆130Updated 2 years ago
- Masked Visual Pre-training for Robotics☆245Updated 2 years ago
- Code for https://jangirrishabh.github.io/lookcloser/☆42Updated 2 years ago
- Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation (2023)☆45Updated 2 years ago
- PyTorch implementation of the Hiveformer research paper☆49Updated 2 years ago
- FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)☆217Updated 10 months ago
- ☆90Updated last year
- Q-attention (within the ARM system) and coarse-to-fine Q-attention (within C2F-ARM system).☆190Updated last year
- [CoRL 2023] XSkill: cross embodiment skill discovery☆66Updated last year
- ☆76Updated last year
- A Benchmark for Evaluating Generalization for Robotic Manipulation☆145Updated 11 months ago
- Official Implementation of RoboCLIP (NeurIPS 2023)☆51Updated last year
- Code for the Behavior Retrieval Paper☆36Updated 2 years ago
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆138Updated 2 years ago
- Code for BAKU: An Efficient Transformer for Multi-Task Policy Learning☆126Updated 10 months ago
- The repository for a thorough empirical evaluation of pre-trained vision model performance across different downstream policy learning me…☆24Updated 2 years ago
- Finetuning Offline World Models in the Real World☆65Updated 2 years ago
- ☆47Updated last year
- Code for Watch and Match: Supercharging Imitation with Regularized Optimal Transport☆83Updated 2 years ago
- Masked World Models for Visual Control☆135Updated 2 years ago
- ☆50Updated last year
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆78Updated last year
- ☆87Updated 6 months ago
- ☆47Updated 2 years ago
- ☆60Updated 2 years ago
- [ICCV 2023] ARNOLD: Language-Grounded Robot Manipulation with Continuous Object States in Realistic 3D Scenes☆180Updated 10 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆30Updated 11 months ago
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆106Updated last year
- Demo-Driven Mobile Bi-Manual Manipulation Benchmark.☆210Updated last week