incognite-lab / myGym
myGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.
☆50Updated this week
Related projects ⓘ
Alternatives and complementary repositories for myGym
- Mujoco Model for UR5-Ridgeback-Robotiq Robot☆37Updated 5 years ago
- Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments (CoRL 2020)☆72Updated last year
- Model definitions and Python API for controlling a Franka Emika Panda robot in the mujoco physics simulator.☆49Updated 2 years ago
- Robot Reinforcement Learning on the Constraint Manifold☆47Updated 2 years ago
- Pybullet version of the multigoal robotics environment from OpenAI Gym☆84Updated last year
- Mujoco Models for the Fetch Robot☆29Updated last year
- [NeurIPS 2021 DDM Workshop] A hybrid control strategy for combining deep RL and classical robotic controllers☆29Updated 2 years ago
- An OpenAI gym environment for the Kuka arm.☆41Updated last year
- Conditional Neural Movement Primitves☆19Updated 3 years ago
- gym RL environment in which a mujoco simulation of Agility Robotics' Cassie robot is rewarded for walking/running forward as fast as poss…☆29Updated 11 months ago
- Verifiably Safe Deep Reinforcement Learning for Robotic Manipulationin Human Environments☆13Updated 2 years ago
- Air Hockey Challenge☆35Updated last month
- Official code (simulation part) for paper Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory Zihan Ding, Ya-Yen Tsai, Wan…☆18Updated 2 years ago
- MuJoCo model of the Franka Emika Robot System☆51Updated 11 months ago
- Model Predictive Actor-Critic Reinforcement Learning☆51Updated 2 years ago
- Official implementation for the UOF paper (algorithm & environment)☆23Updated last year
- Repository containing Robot Servers ROS packages☆29Updated last week
- RL Reach is a platform for running reproducible reinforcement learning experiments.☆42Updated 3 years ago
- Challenging dexterous manipulation environments for RL that extend the hand manipulation environments introduced in OpenAI's Gym☆39Updated 2 years ago
- Learning for Task and Motion Planning (LTAMP)☆51Updated 3 years ago
- ☆57Updated last year
- Franka panda mujoco models☆51Updated 6 months ago
- Steering-based control of a two-wheeled vehicle using RL-PPO and NVIDIA Isaac Gym.☆37Updated 3 years ago
- Package for the dynamic simulation of the Franka Emika Panda robot arm in Gazebo☆65Updated 3 years ago
- Online Replanning in Belief Space for Partially Observable Task and Motion Problems☆63Updated 2 years ago
- A collection of RL gymnasium environments for learning to grasp 3D deformable objects.☆21Updated last month
- Trajectory optimization algorithms for robotic control.☆101Updated last year
- Python3 ROS Interface with the Franka Emika Panda robot arm. Includes support for OpenAI Gym based interfaces.☆28Updated 4 years ago
- IsaacGym environment for Trifinger robot☆41Updated 3 years ago