opendilab/GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).
Provides modular implementations of generative model architectures (diffusion and flow models via score matching and flow matching) integrated directly into RL algorithms like QGPO and IDQL for policy and dynamics learning. Targets gym/D4RL environments with a standardized pipeline that handles state/action representation learning, value-guided generation, and model deployment through a unified API.
189 stars. No commits in the last 6 months. Available on PyPI.
Stars
189
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 18, 2025
Commits (30d)
0
Dependencies
21
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/opendilab/GenerativeRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
soran-ghaderi/torchebm
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.
spqb/adabmDCApy
Pytorch implementation of adabmDCA
kidist-amde/ddro
We introduce the direct document relevance optimization (DDRO) for training a pairwise ranker...
AstraZeneca/DiffAbXL
The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood...
G-U-N/UniRL
a unified reinforcement learning toolbox for joint RL on language models and diffusion models