https://github.com/neka-nat/inv_rl

Inverse Reinforcement Learning Argorithms
https://github.com/neka-nat/inv_rl

chainer inverse-reinforcement-learning openai-gym reinforcement-learning

Last synced: 7 months ago
JSON representation

Inverse Reinforcement Learning Argorithms

• Host: GitHub
• URL: https://github.com/neka-nat/inv_rl
• Owner: neka-nat
• Created: 2017-10-29T16:09:17.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2019-05-13T13:49:16.000Z (over 6 years ago)
• Last Synced: 2025-03-18T13:51:26.834Z (7 months ago)
• Topics: chainer, inverse-reinforcement-learning, openai-gym, reinforcement-learning
• Language: Python
• Size: 31.3 KB
• Stars: 53
• Watchers: 2
• Forks: 10
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Inverse Reinforcement Learning

## Implemented Algorithms

* LP IRL

* Maximum Entropy IRL

* Maximum Entropy Deep IRL

## Reward Map

* Ground Truth

![truth](images/ground_truth.png)

* LP

![lp](images/lp_irl.png)

* Maximum Entropy IRL

![lp](images/max_ent_irl.png)

* Maximum Entropy Deep IRL

![lp](images/max_ent_deep_irl.png)

## Requirements

* OpenAI gym

* numpy

* scipy

* chainer