https://github.com/kanishknavale/generative-adversarial-imitation-learning

Generative Adversial Imitation Learning (GAIL) an inverse reinforcement learning algorithm
https://github.com/kanishknavale/generative-adversarial-imitation-learning

dataset deep-learning dueling-ddqn dueling-dqn-pytorch gail-ppo irl-algorithms python3 pytorch-implementation reinforcement-learning

Last synced: 25 days ago
JSON representation

Generative Adversial Imitation Learning (GAIL) an inverse reinforcement learning algorithm

• Host: GitHub
• URL: https://github.com/kanishknavale/generative-adversarial-imitation-learning
• Owner: KanishkNavale
• License: mit
• Created: 2021-05-02T14:37:15.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-04-05T18:21:36.000Z (almost 3 years ago)
• Last Synced: 2024-11-10T01:13:20.891Z (3 months ago)
• Topics: dataset, deep-learning, dueling-ddqn, dueling-dqn-pytorch, gail-ppo, irl-algorithms, python3, pytorch-implementation, reinforcement-learning
• Language: Python
• Homepage:
• Size: 129 MB
• Stars: 5
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Generative Adversial Imitation Learning

- This repository implements GAIL algorithm.

- The expert policy is based on 'Dueling DQN' algorithm.

- The GAIL is used to clone the expert policy.

- Both the expert and GAIL are developed using PyTroch.

## Expert Profile



## GAIL

    Work in Progress

## Developer

- Name: Kanishk Navale

- Email: [email protected]

- Website: