Vignesh GopalakrishnanResearch Priorities for Robust and Beneficial Artificial IntelligenceStuart Russell (Berkeley), Daniel Dewey (FHI), Max Tegmark (MIT)May 21May 21
Vignesh GopalakrishnanThe Perls of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task…Serena Booth:Bosch The University of Texas at Austin MIT CSAILMay 21May 21
Vignesh GopalakrishnanEfficient and Trustworthy Social Navigation Via Explicit and Implicit Robot-Human CommunicationYuhang Che, Allison M. Okamura, Fellow, IEEE, and Dorsa Sadigh, Member, IEEEMay 21May 21
Vignesh GopalakrishnanA Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical SystemsAnthony Corso acorso@stanford.edu- Aeronautics and Astronautics, Stanford University, Stanford, CA 94305, USAMay 21May 21
Vignesh GopalakrishnanExploiting Procedural Domain Control Knowledge in State-of-the-Art PlannersJorge A. Baier Christian Fritz Sheila A. McIlraith Department of Computer Science, University of Toronto, Toronto, ON M5S 3G4, CANADA…May 21May 21
Vignesh GopalakrishnanDiscovering User-Interpretable Capabilities of Black-Box Planning AgentsPulkit Verma, Shashank Rao Marpally, and Siddharth SrivastavaMay 21May 21
Vignesh GopalakrishnanPrincipal Component AnalysisBasic implementation of Principal Component AnalysisMay 13May 13