Div-Infinity/XQL

Extreme Q-Learning: Max Entropy RL without Entropy

30
/ 100
Emerging

This project offers a novel approach to reinforcement learning (RL) problems, particularly those with a continuous range of possible actions. It provides algorithms that take data from environments or prior interactions and produce optimal action-selection strategies. This is ideal for researchers and practitioners in machine learning who are developing or applying advanced RL agents.

No commits in the last 6 months.

Use this if you are working on reinforcement learning tasks with continuous action spaces and need a more efficient and robust way to estimate optimal 'Q-values' or 'soft-values' for policy improvement.

Not ideal if you are new to reinforcement learning or primarily work with discrete action spaces where traditional Q-learning methods suffice.

reinforcement-learning machine-learning-research robotics-control optimal-control AI-algorithms
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

87

Forks

11

Language

Python

License

Last pushed

Feb 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Div-Infinity/XQL"

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