chengming
/
rsl_rl
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
9 Commits 3 Branches 3 Tags 221 KiB
Python 100%
Go to file
Nikita Rudin 2ad79cf0ca
Update README.md 		2022-03-14 15:09:43 +01:00
licenses/dependencies initial open-source commit 2021-10-27 10:18:22 +02:00
rsl_rl fixes to runner 2021-10-29 18:48:58 +02:00
.gitignore initial open-source commit 2021-10-27 10:18:22 +02:00
LICENSE initial open-source commit 2021-10-27 10:18:22 +02:00
README.md Update README.md 2022-03-14 15:09:43 +01:00
setup.py remove bogus line 2021-11-04 16:17:12 -04:00

README.md

RSL RL

Fast and simple implementation of RL algorithms, designed to run fully on GPU. This code is an evolution of rl-pytorch provided with NVIDIA's Isaac GYM.

Only PPO is implemented for now. More algorithms will be added later. Contributions are welcome.

Setup

git clone https://github.com/leggedrobotics/rsl_rl
cd rsl_rl
pip install -e .

Useful Links

Example use case: https://github.com/leggedrobotics/legged_gym
Project website: https://leggedrobotics.github.io/legged_gym/
Paper: https://arxiv.org/abs/2109.11978

Maintainer: Nikita Rudin
Affiliation: Robotic Systems Lab, ETH Zurich & NVIDIA
Contact: rudinn@ethz.ch