Quentin Gallouédec

Fully open reproduction of DeepSeek-R1

Train transformer language models with reinforcement learning.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Recipes to scale inference-time compute of open models

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Set of robotic environments based on PyBullet physics engine and gymnasium.

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code