openai/random-network-distillation

Stars
861
Rank 52,968 (Top 2 %)
Language
Python
Created about 6 years ago
Updated about 4 years ago

openai/random-network-distillation

openai

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Code for the paper "Exploration by Random Network Distillation"

Status: Archive (code is provided as-is, no updates expected)

Exploration by Random Network Distillation

Yuri Burda*, Harri Edwards*, Amos Storkey, Oleg Klimov
*equal contribution

OpenAI
University of Edinburgh

Installation and Usage

The following command should train an RND agent on Montezuma's Revenge

python run_atari.py --gamma_ext 0.999

To use more than one gpu/machine, use MPI (e.g. mpiexec -n 8 python run_atari.py --num_env 128 --gamma_ext 0.999 should use 1024 parallel environments to collect experience on an 8 gpu machine).

Blog post and videos

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

openai-cookbook

Examples and guides for using the OpenAI API

gym

A toolkit for developing and comparing reinforcement learning algorithms.

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Jupyter Notebook

openai-python

The official Python library for the OpenAI API

gpt-2

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

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

gpt-3

GPT-3: Language Models are Few-Shot Learners

swarm

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

triton

Development repository for the Triton language and compiler

DALL-E

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

shap-e

Generate 3D objects conditioned on text or images

spinningup

An educational resource to help anyone learn deep reinforcement learning.

openai-node

The official Node.js / Typescript library for the OpenAI API

universe

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

jukebox

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

point-e

Point cloud diffusion for 3D model synthesis

consistency_models

Official repo for consistency models.

guided-diffusion

plugins-quickstart

Get a ChatGPT plugin up and running in under 5 minutes!

transformer-debugger

retro

Retro Games in Gym

glide-text2im

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

glow

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

mujoco-py

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

openai-quickstart-node

Node.js example app from the OpenAI API quickstart tutorial

weak-to-strong

improved-gan

Code for the paper "Improved Techniques for Training GANs"

human-eval

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

improved-diffusion

Release for Improved Denoising Diffusion Probabilistic Models

roboschool

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

image-gpt

consistencydecoder

Consistency Distilled Diff VAE

finetune-transformer-lm

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

gpt-2-output-dataset

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

multiagent-particle-envs

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

pixel-cnn

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

openai-quickstart-python

Python example app from the OpenAI API quickstart tutorial

requests-for-research

A living collection of deep learning problems

multi-agent-emergence-environments

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

gpt-discord-bot

Example Discord bot written in Python that uses the completions API to have conversations with the `text-davinci-003` model, and the moderations API to filter the messages.

evolution-strategies-starter

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

generating-reviews-discovering-sentiment

Code for "Learning to Generate Reviews and Discovering Sentiment"

neural-mmo

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

prm800k

800,000 step-level correctness labels on LLM solutions to MATH problems

openai-dotnet

The official .NET library for the OpenAI API

openai-assistants-quickstart

OpenAI Assistants API quickstart with Next.js.

sparse_attention

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

maddpg

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

Video-Pre-Training

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

openai-openapi

OpenAPI specification for the OpenAI API

lm-human-preferences

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

following-instructions-human-feedback

universe-starter-agent

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

dalle-2-preview

InfoGAN

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

grade-school-math

procgen

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

supervised-reptile

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

blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

automated-interpretability

kubernetes-ec2-autoscaler

A batch-optimized scaling manager for Kubernetes

summarize-from-feedback

Code for "Learning to summarize from human feedback"

large-scale-curiosity

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

multiagent-competition

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

imitation

Code for the paper "Generative Adversarial Imitation Learning"

deeptype

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

mlsh

Code for the paper "Meta-Learning Shared Hierarchies"

iaf

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

mujoco-worldgen

Automatic object XML generation for Mujoco

safety-gym

Tools for accelerating safe exploration research.

vdvae

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

coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

robogym

Robotics Gym Environments

weightnorm

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

atari-py

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

openai-security-bots

openai-gemm

Open single and half precision gemm implementations

vime

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

safety-starter-agents

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

ebm_code_release

Code for Implicit Generation and Generalization with Energy Based Models

CLIP-featurevis

code for reproducing some of the diagrams in the paper "Multimodal Neurons in Artificial Neural Networks"

gym-http-api

API to access OpenAI Gym from other languages via HTTP

gym-soccer

sparse_autoencoder

robosumo

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

web-crawl-q-and-a-example

Learn how to crawl your website and build a Q/A bot with the OpenAI API

Jupyter Notebook

phasic-policy-gradient

Code for the paper "Phasic Policy Gradient"

EPG

Code for the paper "Evolved Policy Gradients"

orrb

Code for the paper "OpenAI Remote Rendering Backend"

miniF2F

Formal to Formal Mathematics Benchmark

atari-reset

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

spinningup-workshop

For educational materials related to the spinning up workshops.

train-procgen

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

human-eval-infilling

Code for the paper "Efficient Training of Language Models to Fill in the Middle"

openai-go

The official Go library for the OpenAI API

dallify-discord-bot

Example code for using OpenAI’s NodeJS SDK with discord.js SDK to create a Discord Bot that uses Slash Commands.