ivy-llc/gym

Fully differentiable RL environments, written in Ivy.

38
/ 100
Emerging

This tool helps machine learning researchers and developers explore new ways to train AI agents in simulated environments. It takes standard reinforcement learning tasks, like balancing a pole or controlling a swimmer, and transforms them into a format where the agent's performance can be directly optimized using supervised learning techniques. This allows for a more direct approach to improving AI behavior without needing traditional reinforcement learning methods.

No commits in the last 6 months.

Use this if you are an AI researcher or developer working with reinforcement learning and want to experiment with directly optimizing cumulative rewards in simulated environments using differentiable methods.

Not ideal if you are looking for a simple, out-of-the-box reinforcement learning library for standard agent training without exploring novel differentiable optimization techniques.

reinforcement-learning-research differentiable-simulation AI-agent-training trajectory-optimization machine-learning-experiments
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

66

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Aug 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ivy-llc/gym"

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