2 citations · 2 across the 2 of their papers we have counts for
3 papers
Pixel to policy: DQN Encoders for within & cross-game reinforcement learning
Ashrya Agrawal, Priyanshi Shah, Sourabh Prakash
Reinforcement Learning can be applied to various tasks, and environments. Many of these environments have a similar shared structure, which can be exploited to improve RL performan…
Exploiting CNNs for Semantic Segmentation with Pascal VOC
Sourabh Prakash, Priyanshi Shah, Ashrya Agrawal
In this paper, we present a comprehensive study on semantic segmentation with the Pascal VOC dataset. Here, we have to label each pixel with a class which in turn segments the enti…
Debiasing classifiers: is reality at variance with expectation?
Ashrya Agrawal, Florian Pfisterer, Bernd Bischl +5
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse r…