TianyuCodings/Diffusion_Trusted_Q_Learning

[NeuIPS2024 DTQL] Diffusion Trusted Q-Learning for Offline RL — Official PyTorch Implementation

21
/ 100
Experimental

This project helps machine learning researchers and practitioners who are developing offline reinforcement learning agents. It takes pre-collected datasets of actions and rewards and outputs highly efficient, optimized policies for tasks where data collection is expensive or unsafe. The end user is typically an AI/ML researcher or engineer working on advanced control systems or decision-making algorithms.

No commits in the last 6 months.

Use this if you need to train robust and high-performing offline reinforcement learning policies without needing to collect new data, especially for tasks requiring fast inference and training.

Not ideal if your primary goal is online reinforcement learning where direct interaction with the environment is possible and preferred.

reinforcement-learning offline-RL policy-optimization machine-learning-research decision-making-systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

23

Forks

2

Language

Python

License

Last pushed

May 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TianyuCodings/Diffusion_Trusted_Q_Learning"

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