Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entro

【文件属性】：
文件名称：Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entro
文件大小：5.74MB
文件格式：PDF
更新时间：2023-04-24 08:11:01
machine learning Maximum Causal E Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy Predicting human behavior from a small amount of training examples is a challenging machine learning problem. In this thesis, we introduce the principle of maximum causal entropy, a general technique for applying information theory to decision-theoretic, game-theoretic, and control settings where relevant information is sequentially revealed over time. This approach guarantees decision-theoretic performance by matching purposeful measures of behavior (Abbeel & Ng,2004), and/or enforces game-theoretic rationality constraints (Aumann, 1974), while otherwise being as uncertain as possible, which minimizes worst-case predictive log-loss (Grunwald & Dawid,2003).