M Giegrich, R Oomen, C Reisinger - arXiv preprint arXiv:2306.04836, 2023 - arxiv.org
In this paper, we propose a novel $ K $-nearest neighbor resampling procedure for estimating the performance of a policy from historical data containing realized episodes of a …
Autonomous Mobility-on-Demand (AMoD) systems are an evolving mode of transportation in which a centrally coordinated fleet of self-driving vehicles dynamically serves travel …
Y Jin, Y Zhang, T Qin, X Zhang, J Yuan, H Li… - arXiv preprint arXiv …, 2021 - arxiv.org
Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of …
C Yuan, Y Chandak, S Giguere… - Advances in …, 2021 - proceedings.neurips.cc
Many sequential decision making problems are high-stakes and require off-policy evaluation (OPE) of a new policy using historical data collected using some other policy …
S Yadlowsky - arXiv preprint arXiv:2203.12538, 2022 - arxiv.org
We revisit the classical causal inference problem of estimating the average treatment effect in the presence of fully observed confounding variables using two-stage semiparametric …
ÖZ Bayramoğlu, E Erzin, TM Sezgin… - Proceedings of the 2021 …, 2021 - dl.acm.org
We propose a speech-driven laughter backchannel generation model to reward engagement during human-agent interaction. We formulate the problem as a Markov …
V Liu, Y Chandak, P Thomas… - … Conference on Artificial …, 2023 - proceedings.mlr.press
In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical …
Reinforcement Learning (RL) has recently found many applications in the healthcare domain thanks to its natural fit to clinical decision-making and ability to learn optimal …
Short-and long-term outcomes of an algorithm often differ, with damaging downstream effects. A known example is a click-bait algorithm, which may increase short-term clicks but …