Deep Learning

ADRQN-PyTorch: A Torch implementation of the action-specific deep recurrent Q network.

Deep Q networks have proven to be an easy to implement method for solving control problems in both continuous or large discrete state spaces. The action-specific deep recurrent Q network (ADRQN) introduces an intermediate LSTM layer for remembering action-observation pairs when dealing with partial observability. This post explores a compact PyTorch implementation of the ADRQN including small scale experiments on classical control tasks.

Deep Image Prior: Independently Reproduced in a few lines of PyTorch.

Joint work with Cecilia Casolo and Mats van Tongeren. Published to https://reproducedpapers.org, a TU Delft repository for independent paper reproductions in Computer Vision and Deep Learning.