Example app for the Redux Fundamentals tutorial

Official code for the paper "Offline Meta Learning of Exploration".

A multi-lingual program repair benchmark set based on the Quixey Challenge

An open source robotics benchmark for meta- and multi-task reinforcement learning

Unofficial Pytorch code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

A σ-VAE implementation in PyTorch

Implementation of the Sliced Wasserstein Autoencoder using PyTorch

Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)

https://sites.google.com/view/replab/

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains.

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

Tap containing formulae for casks

Utilities for creating serializable classes

The Variational Homoencoder: Learning to learn high capacity generative models from few examples

Random parameter environments using gym 0.7.4 and mujoco-py 0.5.7

PyTorch code accompanying our paper on Maximum Entropy Generators for Energy-Based Models

A toolkit for developing and comparing reinforcement learning algorithms.