Publications | Andrew Bennetthttps://awbennett.net/publication/PublicationsSource Themes Academic (https://sourcethemes.com/academic/)en-ushttps://awbennett.net/images/icon_hu0b7a4cb9992c9ac0e91bd28ffd38dd00_9727_512x512_fill_lanczos_center_2.pngPublicationshttps://awbennett.net/publication/Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processeshttps://awbennett.net/publication/bennett-2024-efficient/Wed, 25 Sep 2024 00:00:00 +0000https://awbennett.net/publication/bennett-2024-efficient/VQ-TR: Vector Quantized Attention for Time Series Forecastinghttps://awbennett.net/publication/rasul-2024-vqtr/Wed, 08 May 2024 00:00:00 +0000https://awbennett.net/publication/rasul-2024-vqtr/Low-rank MDPs with Continuous Action Spaceshttps://awbennett.net/publication/oprescu-2024-low/Fri, 03 May 2024 00:00:00 +0000https://awbennett.net/publication/oprescu-2024-low/Inference on strongly identified functionals of weakly identified functionshttps://awbennett.net/publication/bennett-2024-inference/Sat, 06 Jan 2024 00:00:00 +0000https://awbennett.net/publication/bennett-2024-inference/Future-Dependent Value-Based Off-Policy Evaluation in POMDPshttps://awbennett.net/publication/uehara-2023-future/Wed, 13 Dec 2023 00:00:00 +0000https://awbennett.net/publication/uehara-2023-future/Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processeshttps://awbennett.net/publication/bennett-2023-proximal/Tue, 26 Sep 2023 00:00:00 +0000https://awbennett.net/publication/bennett-2023-proximal/Source Condition Double Robust Inference on Functionals of Inverse Problemshttps://awbennett.net/publication/bennett-2023-source/Tue, 25 Jul 2023 00:00:00 +0000https://awbennett.net/publication/bennett-2023-source/Minimax Instrumental Variable Regression and L2 Convergence Guarantees without Identification or Closednesshttps://awbennett.net/publication/bennett-2023-minimax/Wed, 12 Jul 2023 00:00:00 +0000https://awbennett.net/publication/bennett-2023-minimax/The Variational Method of Momentshttps://awbennett.net/publication/bennett-2023-variational/Thu, 27 Apr 2023 00:00:00 +0000https://awbennett.net/publication/bennett-2023-variational/Provable Safe Reinforcement Learning with Binary Feedbackhttps://awbennett.net/publication/bennett-2023-provable/Wed, 26 Apr 2023 00:00:00 +0000https://awbennett.net/publication/bennett-2023-provable/Have you tried Neural Topic Models? Comparative Analysis of Neural and Non-Neural Topic Models with Application to COVID-19 Twitter Datahttps://awbennett.net/publication/bennett-2021-have/Sun, 15 Aug 2021 00:00:00 +0000https://awbennett.net/publication/bennett-2021-have/Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confoundershttps://awbennett.net/publication/bennett-2021-off/Thu, 15 Apr 2021 00:00:00 +0000https://awbennett.net/publication/bennett-2021-off/Efficient Policy Learning from Surrogate-Loss Classification Reductionshttps://awbennett.net/publication/bennett-2020-efficient/Wed, 15 Jul 2020 00:00:00 +0000https://awbennett.net/publication/bennett-2020-efficient/Deep Generalized Method of Moments for Instrumental Variable Analysishttps://awbennett.net/publication/bennett-2019-deep/Tue, 10 Dec 2019 00:00:00 +0000https://awbennett.net/publication/bennett-2019-deep/Policy Evaluation with Latent Confounders via Optimal Balancehttps://awbennett.net/publication/bennett-2019-policy/Tue, 10 Dec 2019 00:00:00 +0000https://awbennett.net/publication/bennett-2019-policy/Mapping Instructions to Actions in 3D Environments with Visual Goal Predictionhttps://awbennett.net/publication/misra-2018-mapping/Sat, 03 Nov 2018 00:00:00 +0000https://awbennett.net/publication/misra-2018-mapping/Preferred answer selection in stack overflow: Better text representations... and metadata, metadata, metadatahttps://awbennett.net/publication/xu-2018-preferred/Thu, 01 Nov 2018 00:00:00 +0000https://awbennett.net/publication/xu-2018-preferred/Following High-level Navigation Instructions on a Simulated Quadcopter with Imitation Learninghttps://awbennett.net/publication/blukis-2018-following/Thu, 28 Jun 2018 00:00:00 +0000https://awbennett.net/publication/blukis-2018-following/Detecting Misflagged Duplicate Questions in Community Question-Answering Archiveshttps://awbennett.net/publication/hoogeveen-2018-detecting/Fri, 15 Jun 2018 00:00:00 +0000https://awbennett.net/publication/hoogeveen-2018-detecting/CHALET: Cornell House Agent Learning Environmenthttps://awbennett.net/publication/yan-2018-chalet/Tue, 23 Jan 2018 00:00:00 +0000https://awbennett.net/publication/yan-2018-chalet/LexSemTM: A Semantic Dataset Based on All-words Unsupervised Sense Distribution Learninghttps://awbennett.net/publication/bennett-2016-lexsemtm/Tue, 09 Aug 2016 00:00:00 +0000https://awbennett.net/publication/bennett-2016-lexsemtm/Unsupervised All-words Sense Distribution Learninghttps://awbennett.net/publication/bennett-2016-unsupervised/Wed, 01 Jun 2016 00:00:00 +0000https://awbennett.net/publication/bennett-2016-unsupervised/