S
Shantanu Thakoor
Researcher at Google
Publications - 16
Citations - 554
Shantanu Thakoor is an academic researcher from Google. The author has contributed to research in topics: Computer science & Graph (abstract data type). The author has an hindex of 5, co-authored 10 publications receiving 281 citations. Previous affiliations of Shantanu Thakoor include Stanford University.
Papers
More filters
Book ChapterDOI
The Marabou Framework for Verification and Analysis of Deep Neural Networks
Guy Katz,Derek A. Huang,Duligur Ibeling,Kyle D. Julian,Christopher Lazarus,Rachel Lim,Parth Shah,Shantanu Thakoor,Haoze Wu,Aleksandar Zeljić,David L. Dill,Mykel J. Kochenderfer,Clark Barrett +12 more
TL;DR: Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems, and it performs high-level reasoning on the network that can curtail the search space and improve performance.
Adversarial Examples for Natural Language Classification Problems
TL;DR: The authors showed that up to 90% of input examples admit adversarial perturbations; furthermore, these adversarial examples retain a degree of transferability across models and hint at limitations in our understanding of classification algorithms.
Proceedings ArticleDOI
BYOL-Explore: Exploration by Bootstrapped Prediction
Zhaohan Daniel Guo,Shantanu Thakoor,Miruna Pislar,Bernardo Avila Pires,Florent Altch'e,Corentin Tallec,Alaa Saade,Daniele Calandriello,J.-B. Grill,Yunhao Tang,M Val'ko,Rémi Munos,Mohammad Gheshlaghi Azar,Bilal Piot +13 more
TL;DR: It is shown that BYOL-Explore is effective in DM-HARD-8, a challenging partially-observable continuous-action hard-exploration benchmark with visually-rich 3 -D environments and achieves superhuman performance on the ten hardest exploration games in Atari while having a much simpler design than other competitive agents.
Posted Content
Counterfactual Credit Assignment in Model-Free Reinforcement Learning
Thomas Mesnard,Theophane Weber,Fabio Viola,Shantanu Thakoor,Alaa Saade,Anna Harutyunyan,Will Dabney,Tom Stepleton,Nicolas Heess,Arthur Guez,Marcus Hutter,Lars Buesing,Rémi Munos +12 more
TL;DR: This work adapts the notion of counterfactuals from causality theory to a model-free RL setup and proposes to use these as future-conditional baselines and critics in policy gradient algorithms and develops a valid, practical variant with provably lower variance.
Posted Content
Bootstrapped Representation Learning on Graphs
Shantanu Thakoor,Corentin Tallec,Mohammad Gheshlaghi Azar,Rémi Munos,Petar Veličković,Michal Valko +5 more
TL;DR: Bootstrapped Graph Latents (BGRL) as discussed by the authors is a self-supervised graph representation method based on graph attentional encoder that achieves state-of-the-art results on several established benchmark datasets.