148 citations · 267 across the 12 of their papers we have counts for
7 papers · 1 filter
On Learning to Rank Long Sequences with Contextual Bandits
Anirban Santara, Claudio Gentile, Gaurav Aggarwal +1
Motivated by problems of learning to rank long item sequences, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards an…
Unlocking Pixels for Reinforcement Learning via Implicit Attention
Krzysztof Marcin Choromanski, Deepali Jain, Wenhao Yu +9
There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality an…
ExTra: Transfer-guided Exploration
Anirban Santara, Rishabh Madan, Balaraman Ravindran +1
In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encou…
RAIL: Risk-Averse Imitation Learning
Anirban Santara, Abhishek Naik, Balaraman Ravindran +4
Imitation learning algorithms learn viable policies by imitating an expert's behavior when reward signals are not available. Generative Adversarial Imitation Learning (GAIL) is a s…
Visualization Regularizers for Neural Network based Image Recognition
Biswajit Paria, Vikas Reddy, Anirban Santara +1
The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in…
Ensemble of Deep Convolutional Neural Networks for Learning to Detect Retinal Vessels in Fundus Images
Debapriya Maji, Anirban Santara, Pabitra Mitra +1
Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale sc…
Faster learning of deep stacked autoencoders on multi-core systems using synchronized layer-wise pre-training
Anirban Santara, Debapriya Maji, DP Tejas +2
Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first t…