Rohin Shah

Most-cited papers

On the Utility of Learning about Humans for Human-AI Coordination
Micah Carroll, Rohin Shah, Mark K. Ho, T. Griffiths +3 more
2019Neural Information Processing Systems614 citations
Semantic Scholar
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
Tom Lieberum, Matthew Rahtz, J'anos Kram'ar, Neel Nanda +3 more
2023arXiv.org178 citations Open access
Semantic Scholar
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong +3 more
2022arXiv.org161 citations Open access
Semantic Scholar
Chlorophyll: synthesis-aided compiler for low-power spatial architectures
P. Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla +2 more
2014ACM-SIGPLAN Symposium on Programming Language Design and Implementation152 citations
Semantic Scholar
Optimal Policies Tend To Seek Power
A. Turner, Logan Smith, Rohin Shah, Andrew Critch +1 more
2019Neural Information Processing Systems143 citations
Semantic Scholar
Explaining grokking through circuit efficiency
Vikrant Varma, Rohin Shah, Zachary Kenton, J'anos Kram'ar +1 more
2023arXiv.org123 citations Open access
Semantic Scholar
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
Rohin Shah, Noah Gundotra, P. Abbeel, A. Dragan
2019International Conference on Machine Learning82 citations
Semantic Scholar
Preferences Implicit in the State of the World
Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, P. Abbeel +1 more
2019International Conference on Learning Representations59 citations
Semantic Scholar
Evaluating the Robustness of Collaborative Agents
P. Knott, Micah Carroll, Sam Devlin, K. Ciosek +3 more
2021Adaptive Agents and Multi-Agent Systems43 citations
Semantic Scholar
The MAGICAL Benchmark for Robust Imitation
S. Toyer, Rohin Shah, Andrew Critch, Stuart J. Russell
2020Neural Information Processing Systems43 citations
Semantic Scholar
Beneﬁts of Assistance over Reward Learning
Rohin Shah, Pedro J Freire, Neel Alex, Rachel Freedman +6 more
202040 citations
Semantic Scholar
The MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex +9 more
2021arXiv.org34 citations
Semantic Scholar
Chlorophyll : Synthesis-Aided Compiler for Low-Power Spatial Architectures by Phitchaya Mangpo Phothilimthana
P. Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla +2 more
201532 citations
Semantic Scholar
An Empirical Investigation of Representation Learning for Imitation
Cynthia Chen, Xin Chen, S. Toyer, Cody Wild +9 more
2022NeurIPS Datasets and Benchmarks30 citations Open access
Semantic Scholar
SIRL: Similarity-based Implicit Representation Learning
Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown +1 more
2023IEEE/ACM International Conference on Human-Robot Interaction28 citations Open access
Semantic Scholar
Active Inverse Reward Design
Sören Mindermann, Rohin Shah, Adam Gleave, Dylan Hadfield-Menell
2018arXiv.org22 citations
Semantic Scholar
Choice Set Misspecification in Reward Inference
Rachel Freedman, Rohin Shah, A. Dragan
2021AISafety@IJCAI20 citations
Semantic Scholar
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
Stephanie Milani, A. Kanervisto, Karolis Ramanauskas, Sander Schulhoff +27 more
2023Neural Information Processing Systems19 citations Open access
Semantic Scholar
Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback
Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani +12 more
2022Neural Information Processing Systems10 citations
Semantic Scholar
Learning What To Do by Simulating the Past
David Lindner, Rohin Shah, P. Abbeel, A. Dragan
2021International Conference on Learning Representations4 citations
Semantic Scholar
Combining Reward Information from Multiple Sources
Dmitrii Krasheninnikov, Rohin Shah, Herke van Hoof
2021arXiv.org4 citations
Semantic Scholar
Inferring Reward Functions from Demonstrators with Unknown Biases
Rohin Shah, Noah Gundotra, P. Abbeel, A. Dragan
20184 citations
Semantic Scholar
Retrospective on the 2021 BASALT Competition on Learning from Human Feedback
Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani +12 more
2022arXiv.org1 citations Open access
Semantic Scholar
Automated Incrementalization through Synthesis
Rohin Shah
20171 citations
Semantic Scholar
SIMPL: A DSL for Automatic Specialization of Inference Algorithms
Rohin Shah, Emina Torlak, R. Bodík
2016arXiv.org1 citations
Semantic Scholar
Analyzing Directional Asymmetries in Interoperability among Provider Group Health Information Exchange
Rohin Shah, Josephine Bailey
2022Social Science Research Network0 citations Open access
Semantic Scholar
Extracting and Using Preference Information from the State of the World
Rohin Shah
20200 citations
Semantic Scholar
Preferences Implicit in the State of the World
Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, P. Abbeel +1 more
2018International Conference on Learning Representations0 citations
Semantic Scholar