myosuite
Metaworld
| myosuite | Metaworld | |
|---|---|---|
| 4 | 2 | |
| 772 | 1,117 | |
| 1.8% | 2.4% | |
| 9.2 | 6.2 | |
| 7 days ago | 18 days ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
myosuite
-
MyoSuite: An embodied AI platform that unifies neural and motor intelligence
MyoSuite: A contact-rich simulation suite for musculoskeletal motor control
-
Meta Researchers Introduce a New Embodied AI Platform, Called MyoSuite, That Applies Machine Learning (ML) to Biomechanical Control Problems by Unifying Motor and Neural Intelligence
Continue reading | Check out the paper, Github, blog and project
- GitHub - facebookresearch/myosuite: MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.
Metaworld
-
Looking for Maintainers/Contributors for Metaworld
Right now we're working on doing a big push to dramatically overhaul the Metaworld library (https://github.com/Farama-Foundation/Metaworld), including their API, adding documentation, updating the MuJoCo version, and other massive quality of life features. If anyone would be interested in contributing to this work (and getting your name on an upcoming Metaworld 2.0 paper), please contact Reggie at [email protected].
- MetaWorld has joined the Farama Foundation
What are some alternatives?
MuJoCo_RL_UR5 - A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.
garage - A toolkit for reproducible reinforcement learning research.
DI-engine - OpenDILab Decision AI Engine
tianshou - An elegant PyTorch deep reinforcement learning library.
dm_control - Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
pytorch-a2c-ppo-acktr-gail - PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).