christopherhesse

Christopher Hesse's repositories

atari-demo

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

Language:PythonMIT000

atari-reset

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

Language:PythonMIT000

deeptype

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

Language:PythonNOASSERTION000

EPG

Code for the paper "Evolved Policy Gradients"

Language:PythonMIT000

evolution-strategies-starter

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

Language:PythonMIT000

finetune-transformer-lm

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

Language:PythonMIT000

generating-reviews-discovering-sentiment

Code for "Learning to Generate Reviews and Discovering Sentiment"

Language:PythonMIT000

glow

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

Language:PythonMIT000

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Language:PythonNOASSERTION000

iaf

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

Language:PythonMIT000

imitation

Code for the paper "Generative Adversarial Imitation Learning"

Language:PythonMIT000

improved-gan

Code for the paper "Improved Techniques for Training GANs"

Language:Python000

InfoGAN

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

Language:Python000

large-scale-curiosity

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

Language:Python000

maddpg

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

Language:PythonMIT000

mlsh

Code for the paper "Meta-Learning Shared Hierarchies"

Language:Python000

mujoco-py

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

Language:PythonNOASSERTION000

multiagent-competition

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

Language:Python000

multiagent-particle-envs

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

Language:PythonMIT000

neural-gpu

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

Language:Python000

ot-gan

Code for the paper "Improving GANs Using Optimal Transport"

Language:Jupyter NotebookMIT000

pixel

Code for a single pixel debate game from the paper "AI safety via debate" https://arxiv.org/abs/1805.00899

Language:JavaScriptMIT000

pixel-cnn

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

Language:PythonMIT000

retro

Retro Games in Gym

Language:C++MIT000

roboschool

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

Language:PythonNOASSERTION000

signup-forms

Code for the paper "World of Bits: An Open-Domain Platform for Web-Based Agents"

Language:CSS000

spinningup

An educational resource to help anyone learn deep reinforcement learning.

Language:PythonMIT000

supervised-reptile

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

Language:JavaScriptMIT000

vime

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

Language:Python000

weightnorm

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

Language:PythonMIT000