2 citations · 2 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
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…
cs.LG2020
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…