haron1100/Upside-Down-Reinforcement-Learning
Implementation of Schmidhuber's Upside Down Reinforcement Learning paper in PyTorch
This project helps machine learning researchers and practitioners explore an alternative approach to reinforcement learning. It takes desired outcomes, like a target reward and episode length, and outputs the optimal actions a learning agent should take. This is useful for those who want to experiment with goal-conditioned policies without defining explicit reward functions or complex training loops.
No commits in the last 6 months.
Use this if you are a reinforcement learning researcher or practitioner interested in experimenting with 'upside-down' or goal-conditioned learning paradigms for your agents.
Not ideal if you are looking for a plug-and-play solution for a business problem, as this is an experimental research implementation.
Stars
27
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 16, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/haron1100/Upside-Down-Reinforcement-Learning"
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