https://github.com/rlopensource/generative_adversarial_imitation_learning

https://github.com/rlopensource/generative_adversarial_imitation_learning

gail generative-adversarial-network imitation-learning proximal-policy-optimization reinforcement-learning

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/rlopensource/generative_adversarial_imitation_learning
• Owner: RLOpensource
• Created: 2019-09-03T11:02:04.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2019-09-03T11:34:16.000Z (almost 7 years ago)
• Last Synced: 2025-06-06T08:04:25.756Z (about 1 year ago)
• Topics: gail, generative-adversarial-network, imitation-learning, proximal-policy-optimization, reinforcement-learning
• Language: Python
• Size: 327 KB
• Stars: 7
• Watchers: 0
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Generative Adversarial Imitation Learning

## Gym environment

* Env==CartPole-v0

* State==Continuous

* Action==Discrete

## Generate expert data

Generate expert data by ppo

```

python get_expert_data.py

```

## Imitation Learning

```

python main.py

```

## Result

* orange : gail

* blue : ppo



  

  





  

  



## Reference

[1] [Generative Adversarial Imitation Learning](https://papers.nips.cc/paper/6391-generative-adversarial-imitation-learning.pdf)