Div-Infinity/XQL
Extreme Q-Learning: Max Entropy RL without Entropy
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.
Stars
87
Forks
11
Language
Python
License
—
Category
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.
Higher-rated alternatives
qgallouedec/panda-gym
Set of robotic environments based on PyBullet physics engine and gymnasium.
nicrusso7/rex-gym
OpenAI Gym environments for an open-source quadruped robot (SpotMicro)
amazon-science/auction-gym
AuctionGym is a simulation environment that enables reproducible evaluation of bandit and...
upb-lea/openmodelica-microgrid-gym
OpenModelica Microgrid Gym (OMG): An OpenAI Gym Environment for Microgrids
vietnh1009/Super-mario-bros-A3C-pytorch
Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros