Welcome to State Representation Learning Zoo’s documentation!

A collection of State Representation Learning (SRL) methods for Reinforcement Learning, written using PyTorch.

Github repo: https://github.com/araffin/srl-zoo

Note

This repo is part of the S-RL Toolbox

Available methods:

  • SRL with Robotic Priors + extensions (stereovision, additional priors)
  • Denoising Autoencoder (DAE)
  • Variational Autoencoder (VAE) and beta-VAE
  • PCA
  • Supervised Learning
  • Forward, Inverse Models
  • Triplet Network (for stereovision only)
  • Reward loss
  • Combination and stacking of methods
  • Random Features
  • [experimental] Reward Prior, Episode-prior, Perceptual Similarity loss (DARLA), Mutual Information loss

Related papers:

Indices and tables