https://github.com/aprimadi/deep-rl-imitation
Deep Reinforcement Learning - Imitation Learning
https://github.com/aprimadi/deep-rl-imitation
behavioral-cloning dagger deep-reinforcement-learning imitation-learning tensorflow
Last synced: 6 months ago
JSON representation
Deep Reinforcement Learning - Imitation Learning
- Host: GitHub
- URL: https://github.com/aprimadi/deep-rl-imitation
- Owner: aprimadi
- Created: 2019-04-17T18:47:32.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2022-12-08T04:59:46.000Z (almost 3 years ago)
- Last Synced: 2025-04-24T23:15:21.809Z (6 months ago)
- Topics: behavioral-cloning, dagger, deep-reinforcement-learning, imitation-learning, tensorflow
- Language: Python
- Size: 706 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Imitation Learning
Dependencies:
* Python **3.5**
* Numpy version **1.14.5**
* TensorFlow version **1.10.5**
* MuJoCo version **1.50** and mujoco-py **1.50.1.56**
* OpenAI Gym version **0.10.5**
Once Python **3.5** is installed, you can install the remaining dependencies using `pip install -r requirements.txt`.
**Note**: MuJoCo versions until 1.5 do not support NVMe disks therefore won't be compatible with recent Mac machines.
There is a request for OpenAI to support it that can be followed [here](https://github.com/openai/gym/issues/638).
In `experts/`, the provided expert policies are:
* Ant-v2.pkl
* HalfCheetah-v2.pkl
* Hopper-v2.pkl
* Humanoid-v2.pkl
* Reacher-v2.pkl
* Walker2d-v2.pkl
The name of the pickle file corresponds to the name of the gym environment.
## Running test
```
pytest
```
With coverage:
```
coverage run -m pytest
coverage html
```