BY571/Upside-Down-Reinforcement-Learning

Upside-Down Reinforcement Learning (⅂ꓤ) implementation in PyTorch. Based on the paper published by Jürgen Schmidhuber.

41
/ 100
Emerging

This project offers an implementation of Upside-Down Reinforcement Learning for developing intelligent agents. It takes a desired reward and time horizon as input, then trains an agent to achieve those goals in environments like CartPole or LunarLander. It's designed for researchers and practitioners exploring alternative reinforcement learning paradigms.

No commits in the last 6 months.

Use this if you are a machine learning researcher or student experimenting with advanced reinforcement learning techniques, specifically Upside-Down RL, for discrete or continuous control problems.

Not ideal if you need a production-ready reinforcement learning solution or are looking for a standard, widely adopted RL algorithm for immediate application.

reinforcement-learning AI-research intelligent-agents control-systems machine-learning-experimentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

78

Forks

12

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 13, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BY571/Upside-Down-Reinforcement-Learning"

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