Verifiers for LLM Reinforcement Learning

Learning Formal Mathematics from Intrinsic Motivation

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

An environment for learning formal mathematical reasoning from scratch

Practically and asymptotically accurate conditional sampling from diffusion generative models without conditional training

Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (+ images)

High-Resolution Image Synthesis with Latent Diffusion Models

GFlowNet library

Deep Batch Active Learning for Regression

Code to reproduce active learning experiments in "Multi-Objective GFlowNets" (Jain et al 2023)

GFlowNet related training and environment code

Benchmarks for Model-Based Optimization

Official code for Long Expressive Memory (ICLR 2022, Spotlight)

path integral sampler (ICLR2022)

This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Python Multi-Agent Reinforcement Learning framework

SMAC: The StarCraft Multi-Agent Challenge

Tensors and Dynamic neural networks in Python with strong GPU acceleration

disentanglement_lib is an open-source library for research on learning disentangled representations.

Please do not feed the models