aravindr93/mjrl
A Python package implementing reinforcement learning algorithms for continuous control tasks in MuJoCo physics simulation.
Not currently ranked — collecting fresh signals.
star history
This repository provides implementations of various reinforcement learning algorithms designed for continuous control tasks in the MuJoCo physics simulation environment. It includes algorithms such as TRPO and PPO for policy optimization. The package uses PyTorch as the underlying deep learning framework and gym for the environment interface. The algorithms are applied to robotics tasks including dexterous manipulation, addressing generalization and simplicity in continuous control.
Frequently asked
- What is aravindr93/mjrl?
- A Python package implementing reinforcement learning algorithms for continuous control tasks in MuJoCo physics simulation.
- Is mjrl open source?
- Yes — aravindr93/mjrl is open source, released under the Apache-2.0 license.
- What language is mjrl written in?
- aravindr93/mjrl is primarily written in Python.
- How popular is mjrl?
- aravindr93/mjrl has 464 stars on GitHub.
- Where can I find mjrl?
- aravindr93/mjrl is on GitHub at https://github.com/aravindr93/mjrl.