pathak22/exploration-by-disagreement
[ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement
This project helps researchers and engineers develop intelligent agents that can learn new skills by exploring environments on their own, without needing constant external rewards. It takes in environment data (like from games or robotics) and outputs an agent that has learned effective exploration strategies. It's designed for machine learning researchers, AI practitioners, and robotics engineers working on self-supervised learning.
129 stars. No commits in the last 6 months.
Use this if you need an agent to efficiently discover and learn behaviors in complex, unfamiliar environments without explicit rewards.
Not ideal if your problem requires an agent to optimize for a specific, well-defined reward signal using traditional reinforcement learning.
Stars
129
Forks
22
Language
Python
License
—
Category
Last pushed
Jun 11, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pathak22/exploration-by-disagreement"
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