Posts by Collection



DSR Reinforcement Learning to navigate a Labyrinth

Published in , 1900

Generalized Successor Representations from Neuroscience within an end-to-end deep reinforcement learning framework, comparing its efficacy to DQN on two diverse environments (Mazebase and DOOM) given raw pixel observations.

Exploring the Efficiency of Capsule Networks in GANs

Published in , 1900

Used capsule network as discriminator for a generative adversarial network, trained using several hacks, which outperformed CNN-GANs at modeling image data distribution of mnist, cifar10 and celebA