Decision making using minimization of regret
نویسندگان
چکیده
منابع مشابه
Geometric Operators in Decision Making with Minimization of Regret
We study different types of aggregation operators and the decision making process with minimization of regret. We analyze the original work developed by Savage and the recent work developed by Yager that generalizes the MMR method creating a parameterized family of minimal regret methods by using the ordered weighted averaging (OWA) operator. We suggest a new method that uses different types of...
متن کاملRegret in Decision Making
Decision research has only recently started to take seriously the role of emotions in choices and decisions. Regret is the emotion that has received the most attention. In this article, we sample a number of the initial regret studies from psychology and economics, and trace some of the complexities and contradictions to which they led. We then sketch a new theory, decision justification theory...
متن کاملRegret Minimization in Nonstationary Markov Decision Processes
We consider decision-making problems in Markov decision processes where both the rewards and the transition probabilities vary in an arbitrary (e.g., nonstationary) fashion to some extent. We propose online learning algorithms and provide guarantees on their performance evaluated in retrospect against stationary policies. Unlike previous works, the guarantees depend critically on the variabilit...
متن کاملPricing Exotic Derivatives Using Regret Minimization
We price various financial instruments, which are classified as exotic options, using the regret bounds of an online algorithm. In addition, we derive a general result, which upper bounds the price of any derivative whose payoff is a convex function of the final asset price. The market model used is adversarial, making our price bounds robust. Our results extend the work of [9], which used regr...
متن کاملEfficient Constrained Regret Minimization
Online learning constitutes a mathematical and compelling framework to analyze sequential decision making problems in adversarial environments. The learner repeatedly chooses an action, the environment responds with an outcome, and then the learner receives a reward for the played action. The goal of the learner is to maximize his total reward. However, there are situations in which, in additio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Approximate Reasoning
سال: 2004
ISSN: 0888-613X
DOI: 10.1016/j.ijar.2003.10.003