82 open source projects by openai

Code for the paper "Large-Scale Study of Curiosity-Driven Learning"

Code for the paper "Emergent Complexity via Multi-agent Competition"

Code for the paper "DeepType: Multilingual Entity Linking by Neural Type System Evolution"

Code for the paper "Generative Adversarial Imitation Learning"

Code for the paper "Meta-Learning Shared Hierarchies"

A toolkit for developing and comparing reinforcement learning algorithms.

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

Code for the paper "Jukebox: A Generative Model for Music"

Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"

Automatic object XML generation for Mujoco

Code for the paper "Curiosity-driven Exploration in Deep Reinforcement Learning via Bayesian Neural Networks"

Code for the paper "Quantifying Transfer in Reinforcement Learning"

Open single and half precision gemm implementations

Contrastive Language-Image Pretraining

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

No description, website, or topics provided.

Submissions for AI and Efficiency SOTA's

OpenAI Retro Contest

[deprecated] Bridge from Gym to ROS robots

No description, website, or topics provided.

GLIDE: a diffusion-based text-conditional image synthesis model

Code for the Neural GPU model originally described in "Neural GPUs Learn Algorithms"

Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"

Wikipedia navigation environment for OpenAI Gym

Training Sonic with RLlib

Code for the paper "Improving GANs Using Optimal Transport"

Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.

Release for Improved Denoising Diffusion Probabilistic Models

Learned Hyperparameter Optimizers

Code for the paper "Evaluating Large Language Models Trained on Code"

No description, website, or topics provided.