nikhilbarhate99/min-decision-transformer

Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in OpenAI gym

41
/ 100
Emerging

This tool helps machine learning engineers and researchers implement and experiment with the Decision Transformer model for robotic control tasks. It takes pre-recorded demonstration data of an agent performing actions in a simulated environment, like a robot arm or a humanoid figure, and outputs a trained model that can predict future actions to achieve a desired outcome. This allows for training intelligent agents from existing demonstrations rather than extensive trial-and-error.

288 stars. No commits in the last 6 months.

Use this if you are an ML researcher working on offline reinforcement learning and need a streamlined, efficient PyTorch implementation of the Decision Transformer for Mujoco control environments.

Not ideal if you are looking for a general-purpose reinforcement learning library or need to train agents in real-world physical environments without simulation.

reinforcement-learning robotics-simulation offline-rl sequential-decision-making control-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

288

Forks

29

Language

Python

License

MIT

Last pushed

Jun 10, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nikhilbarhate99/min-decision-transformer"

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