Cooperative Inverse Reinforcement Learning

This repository work done at AISC3 towards replicating and extending CIRL (paper).

The implementations of IRL are taken from neka-nat and the environments are created in OpenAI gym

Implemented Algorithms

Name		Name	Last commit message	Last commit date
Latest commit History 40 Commits
envs		envs
images		images
.gitignore		.gitignore
README.md		README.md
cirl.py		cirl.py
cirl_interupt.py		cirl_interupt.py
lp_irl.py		lp_irl.py
max_ent_deep_irl.py		max_ent_deep_irl.py
max_ent_irl.py		max_ent_irl.py
requirements.txt		requirements.txt
value_iteration.py		value_iteration.py