nke001

causal_learning_unknown_interventions

Code for "Neural causal learning from unknown interventions"

sparse_attentive_backtracking_release

Code for our paper "Sparse Attentive Backtracking: Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding" https://papers.nips.cc/paper/7991-sparse-attentive-backtracking-temporal-credit-assignment-through-reminding.pdf

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

c-swm-1

Contrastive Learning of Structured World Models

causal_induction

Codebase for "Causal Induction from Visual Observations for Goal-Directed Tasks"

coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

doodad

A job launching library for docker, EC2, etc.

gated-path-planning-networks

GitPython

GitPython is a python library used to interact with Git repositories.

guided-evolutionary-strategies

Guided Evolutionary Strategies

gym-minigrid

Minimalistic gridworld environment for OpenAI Gym

mrcl

Code for the NeurIPS19 paper "Meta-Learning Representations for Continual Learning"

mujoco-py

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

nke001.github.io

omniglot

Omniglot data set for one-shot learning

pytorch-a2c-ppo

A recurrent, multi-process and readable PyTorch implementation of the deep reinforcement algorithms A2C and PPO

pytorch-a2c-ppo-acktr

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

pytorch-maml

PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400

pytorch-noreward-rl

pytorch implementation of Curiosity-driven Exploration by Self-supervised Prediction

pytorch-trpo

PyTorch implementation of Trust Region Policy Optimization

Pytorch-UNet

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

pytorchrl

Deep Reinforcement Learning algorithms implemented in PyTorch

retro

Retro Games in Gym

retro-baselines

Publicly releasable baselines for the Retro contest

rlkit

Collection of reinforcement learning algorithms

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

Sectar

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

spriteworld

Spriteworld: a flexible, configurable python-based reinforcement learning environment

STOVE

Anonymous ICLR 2020 Submission: Structured Object-Aware Physics Prediction for Video Modelling and Planning

WorldModelsExperiments

World Models Experiments