TroddenSpade/Maximum-Entropy-Deep-IRL

Implementations of Maximum Entropy Algorithms for solving Inverse Reinforcement Learning problems.

19
/ 100
Experimental

This project helps machine learning researchers understand and replicate complex behaviors by observing an 'expert' agent's actions in a simulated environment. It takes demonstrations of desired behavior (e.g., how an agent navigates a grid) and outputs a reward function that explains why the expert acted that way, allowing other agents to learn similar optimal strategies. This is ideal for researchers working on imitation learning or behavior cloning.

No commits in the last 6 months.

Use this if you need to infer the underlying motivations or reward structure from observed expert demonstrations in simulation environments like 'Gridworld' or 'ObjectWorld'.

Not ideal if you are looking to train a reinforcement learning agent from scratch without expert demonstrations, or if your primary goal is real-world robotic control outside of a simulated context.

imitation-learning behavior-cloning reinforcement-learning-research agent-modeling simulated-environments
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

29

Forks

1

Language

Jupyter Notebook

License

Last pushed

Nov 04, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TroddenSpade/Maximum-Entropy-Deep-IRL"

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