Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
| Date | Stars |
|---|---|
| 2026-07-30 | 1072 |
| 2026-08-10 | 1074 |
| 2026-08-18 | 1081 |
| 2026-08-19 | 1083 |
| 2026-08-21 | 1082 |
| 2026-08-25 | 1084 |
| 2026-08-27 | 1085 |
| 2026-08-28 | 1087 |
| 2026-08-30 | 1088 |
| 2026-08-31 | 1089 |
| 2026-09-02 | 1091 |
| 2026-09-03 | 1092 |
| 2026-09-04 | 1093 |
| 2026-09-07 | 1094 |
| 2026-09-08 | 1096 |
| 2026-09-09 | 1097 |
| 2026-09-10 | 1098 |
| 2026-09-11 | 1099 |
| 2026-09-14 | 1100 |
| 2026-09-16 | 1101 |
| 2026-09-20 | 1102 |
| 2026-09-22 | 1103 |
| 2026-09-23 | 1104 |
| 2026-09-27 | 1105 |
| 2026-09-28 | 1106 |
| 2026-09-29 | 1107 |
| 2026-10-07 | 1109 |
| 2026-10-08 | 1109 |
| 2026-10-11 | 1111 |
| 2026-10-12 | 1113 |
| 2026-10-13 | 1114 |
| 2026-10-14 | 1115 |
| 2026-10-15 | 1116 |
| 2026-10-18 | 1117 |
| 2026-10-19 | 1118 |
| 2026-10-20 | 1119 |
| 2026-10-21 | 1118 |
| 2026-10-29 | 1119 |
| 2026-11-02 | 1120 |
| 2026-11-04 | 1119 |
Today
-1 stars today
This week
+1 stars this week
This month
+12 stars this month
Momentum
0.0
growth rate 0.09%/day
# Bi-DexHands: Bimanual Dexterous Manipulation via Reinforcement Learning <img src="assets/image_folder/coverv3.jpg" width="1000" border="1"/> **** [](https://pypi.org/project/bidexhands/) [](https://github.com/PKU-MARL "Organization") [](https://github.com/PKU-MARL "Unittest") [](https://github.com/PKU-MARL "Docs") [](https://github.com/PKU-MARL/DexterousHands/blob/main/LICENSE) ### Update [2023/02/09] We re-package the Bi-DexHands. Now you can call the Bi-DexHands' environments not only on the command line, but also in your Python script. check our README [Use Bi-DexHands in Python scripts](#Use-Bi-DexHands-in-Python-scripts) below. [2022/11/24] Now we support visual observation for all the tasks, check this [document for visual input](#./docs/visual-in.md). [2022/10/02] Now we support for the default IsaacGymEnvs RL library [rl-games](https://github.com/Denys88/rl_games), check our README [below](#Use-rl_games-to-train-our-tasks). **Bi-DexHands** ([click bi-dexhands.ai](https://pku-marl.github.io/DexterousHands/)) provides a collection of bimanual dexterous manipulations tasks and reinforcement learning algorithms. Reaching human-level sophistication of hand dexterity and bimanual coordination remains an open challenge for modern robotics researchers. To better help the community study this problem, Bi-DexHands are developed with the following key features: - **Isaac Efficiency**: Bi-DexHands is built within [Isaac Gym](https://developer.nvidia.com/isaac-gym); it supports running thousands of environments simultaneously. For example, on one NVIDIA RTX 3090 GPU, Bi-DexHands can reach **40,000+ mean FPS** by running 2,048 environments in parallel. - **Comprehensive RL Benchmark**: we provide the first bimanual manipulation task environment for RL, MARL, Multi-task RL, Meta RL, and Offline RL practitioners, along with a comprehensive benchmark for SOTA continuous control model-free RL/MARL methods. See [example](./bidexhands/algorithms/marl/) - **Heterogeneous-agents Cooperation**: Agents in Bi-DexHands (i.e., joints, fingers, hands,...) are genuinely heterogeneous; this is very different from common multi-agent environments such as [SMAC](https://github.com/oxwhirl/smac) where agents can simply share parameters to solve the task. - **Task Generalization**: we introduce a variety of dexterous manipulation tasks (e.g., handover, lift up, throw, place, put...) as well as enormous target objects from the [YCB](https://rse-lab.cs.washington.edu/projects/posecnn/) and [SAPIEN](https://sapien.ucsd.edu/) dataset (>2,000 objects); this allows meta-RL and multi-task RL algorithms to be tested on the task generalization front. - **Point Cloud**: We provide the ability to use point clouds as observations. We used the depth camera in Isaacc Gym to get the depth image and then convert it to partial point cloud. We can customize the pose and numbers of depth cameras to get point cloud from difference angles. The density of generated point cloud depends on the number of the camera pixels. See the [visual input docs](./docs/point-cloud.md). - **Quick Demos** <div align=center> <img src="assets/image_folder/quick_demo3.gif" align="center" width="600"/> </div> Contents of this repo are as follows: - [Installation](#Installation) - [Pre-requisites](#Installation) <!-- - [Install from PyPI](#Install-from-PyPI) --> - [Install from source code](#Install-from-source-code) - [Introduction to Bi-DexHands](#Introduction-to-Bi-DexHands) - [Overview of Environments](./docs/environments.md) - [Overview of Algorithms](./docs/algorithms.md) - [Getting Started](#Gett
Excerpt of 30,177 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f83d70e4dcf8968f, topic:reinforcement-learning, topic:deep-reinforcement-learning, readme:reinforcement learning
