Difference of convex functions programming for policy optimization in reinforcement learning

• المؤلف الرئيسي: KUMAR, Akshat
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: Agent policy; Reinforcement learning optimization; Difference-of-convex functions; Reinforcement learning algorithm; Artificial Intelligence and Robotics
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/9926; https://ink.library.smu.edu.sg/context/sis_research/article/10926/viewcontent/ConvexFunctionsProg_pvoa_cc_by.pdf
• المؤسسة: Singapore Management University

We formulate the problem of optimizing an agent's policy within the Markov decision process (MDP) model as a difference-of-convex functions (DC) program. The DC perspective enables optimizing the policy iteratively where each iteration constructs an easier-to-optimize lower bound on the value f...