82 open source projects by openai

API to access OpenAI Gym from other languages via HTTP

Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"

Code for Implicit Generation and Generalization with Energy Based Models

Tools for accelerating safe exploration research.

Code for the paper "Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments"

A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface

Robotics Gym Environments

Code for the paper "Language Models are Unsupervised Multitask Learners"

Code for "Learning to summarize from human feedback"

Retro Games in Gym

Code for the paper "Evolved Policy Gradients"

Code for the paper "OpenAI Remote Rendering Backend"

PyTorch package for the discrete VAE used for DALL·E.

Code for the paper "Improved Techniques for Training GANs"

DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.

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

For educational materials related to the spinning up workshops.

Code for the paper Fine-Tuning Language Models from Human Preferences

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Publicly releasable baselines for the Retro contest

A living collection of deep learning problems

Code for the paper "Phasic Policy Gradient"

Code for "Learning to Generate Reviews and Discovering Sentiment"

Fast VNC driver

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

Vectorized interface for reinforcement learning environments

ViZDoom Python wrapper

Dataset of GPT-2 outputs for research in detection, biases, and more

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

A starter agent that can solve a number of universe environments.

Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"

Python wrappers for Pachi. Contains a modified version of the bleeding-edge Pachi source code.

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Code for the paper "On First-Order Meta-Learning Algorithms"

A batch-optimized scaling manager for Kubernetes

Efficient GPU kernels for block-sparse matrix multiplication and convolution

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

An educational resource to help anyone learn deep reinforcement learning.

Code for the paper "Exploration by Random Network Distillation"