Michael Laskin

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

MishaLaskin

RAD: Reinforcement Learning with Augmented Data

MishaLaskin

TorchingUp provides minimal implementations of common Reinforcement Learning algorithms written in PyTorch. It is meant to complement OpenAI’s SpinningUp repository, which contains similar algorithms...

MishaLaskin

A pytorch implementation of the vector quantized variational autoencoder (https://arxiv.org/abs/1711.00937)

MishaLaskin