sibmr/IRLSeminar-MaximumEntropyInverseReinforcementLearning

Maximum Entropy Inverse Reinforcement Learning on the FrozenLake-v0-8x8 environment.

13
/ 100
Experimental

This project helps researchers and students in artificial intelligence understand and apply Inverse Reinforcement Learning (IRL) to teach an AI how to make decisions by observing expert demonstrations. You provide examples of an expert's actions in an environment, and the system outputs an understanding of the expert's underlying goals. This is designed for those studying or working with AI decision-making.

No commits in the last 6 months.

Use this if you are an AI researcher or student learning about or implementing Maximum Entropy Inverse Reinforcement Learning to infer rewards from expert behavior.

Not ideal if you are looking for a plug-and-play solution for real-world reinforcement learning applications outside of a research or study context.

artificial-intelligence-research reinforcement-learning inverse-reinforcement-learning machine-learning-education robot-learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Jupyter Notebook

License

Category

lunar-lander-rl

Last pushed

Apr 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sibmr/IRLSeminar-MaximumEntropyInverseReinforcementLearning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.