The simplest, fastest repository for training/finetuning medium-sized GPTs.

Benchmarking the Spectrum of Agent Capabilities

TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.

Pointax: PointMaze Environment for JAX

An environment for learning formal mathematical reasoning from scratch

LLM as World Models using Bayesian inference

Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.

Curiosity driven exploration of your complex system 👀

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

LLM training in simple, raw C/CUDA

Python client library for Mistral AI platform

Official inference library for Mistral models

(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation

Code for conservative Q-learning

A library of reinforcement learning components and agents

Awesome Open-ended AI

Projet en équipe pour le cours d'application web de l'ENSEEIHT.

Behavioural cloning experiments with video games

Projet de programmation fonctionnelle de l'ENSEEIHT en 2A SN-L