Manipulating adaptive processes by constructive training-time attacks

• المؤلف الرئيسي: Bector, Ridhima
• مؤلفون آخرون: Zinovi Rabinovich
• التنسيق: Thesis-Doctor of Philosophy
• اللغة: English
• منشور في: Nanyang Technological University 2024
• الموضوعات: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/173190
• المؤسسة: Nanyang Technological University

Over the last decade, Reinforcement Learning (RL) has dramatically altered the sequential decision-making landscape and has produced several AI breakthroughs such as AlphaGo, Pluribus, and AlphaStar which are RL-based Artificial Intelligence (AI) that have achieved superhuman proficiency in challeng...