TroddenSpade/Maximum-Entropy-Deep-IRL
Implementations of Maximum Entropy Algorithms for solving Inverse Reinforcement Learning problems.
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.
Stars
29
Forks
1
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild