Systems and methods for utilizing recursive inference graphs in multi-subject reinforcement learning

• Main Authors: ISELE DAVID F, KOCIENDEFER, MICHAEL, J, MA XIAOBAI, GUPTA, JAYANT, K
• Format: Patent
• Language: Chinese; English
• Published: 29.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

Systems and methods for utilizing a recursive inference graph in multi-subject reinforcement learning, the systems and methods comprising: receiving data associated with a self-subject and a target subject traveling within a multi-subject environment; and analyzing the data associated with the self-subject and the target subject using a multi-subject central participant reviewer framework. The system and method also include performing k-level recursive reasoning based on the multi-subject participant reviewer framework to compute higher-level recursive actions for the self-subject and the target subject. The system and method also includes controlling at least one of the self-ongoing subject and the target subject to operate within the multi-subject environment based on at least one of: a subject action policy associated with the self-ongoing subject and a subject action policy associated with the target subject. 用于在多主体强化学习中利用递归推理图的系统和方法，所述系统和方法包括：接收与在多主体环境内行进的自我主体和目标主体相关联的数据；以及利用多主体中心参与者评论者框架分析与所述自我主体和所述目标主体