https://github.com/ikostrikov/walk_in_the_park
https://github.com/ikostrikov/walk_in_the_park
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ikostrikov/walk_in_the_park
- Owner: ikostrikov
- License: mit
- Created: 2022-08-16T20:01:15.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-08-20T21:04:12.000Z (about 3 years ago)
- Last Synced: 2025-06-20T11:10:08.491Z (4 months ago)
- Language: Python
- Size: 9.92 MB
- Stars: 266
- Watchers: 10
- Forks: 37
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# A Walk in the Park
Code to replicate [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://arxiv.org/abs/2208.07860), which contains code for training a simulated or real A1 quadrupedal robot to walk. Project page: https://sites.google.com/berkeley.edu/walk-in-the-park
## Installation
Install dependencies:
```bash
pip install -r requirements.txt
```
To install the robot [SDK](https://github.com/unitreerobotics/unitree_legged_sdk), first install the dependencies in the README.md
To build, run:
```bash
cd real/third_party/unitree_legged_sdk
mkdir build
cd build
cmake ..
make
```
Finally, copy the built `robot_interface.XXX.so` file to this directory.
## Training
Example command to run simulated training:
```bash
MUJOCO_GL=egl XLA_PYTHON_CLIENT_PREALLOCATE=false python train_online.py --env_name=A1Run-v0 \
--utd_ratio=20 \
--start_training=1000 \
--max_steps=100000 \
--config=configs/droq_config.py
```
To run training on the real robot, add `--real_robot=True`