Dynamic programming is optimal for certain sequential decision processes
نویسندگان
چکیده
منابع مشابه
Faster Dynamic Programming for Markov Decision Processes
Markov decision processes (MDPs) are a general framework used in artificial intelligence (AI) to model decision theoretic planning problems. Solving real world MDPs has been a major and challenging research topic in the AI literature, since classical dynamic programming algorithms converge slowly. We discuss two approaches in expediting dynamic programming. The first approach combines heuristic...
متن کاملMarkov Decision Processes: Discrete Stochastic Dynamic Programming
The Wiley-Interscience Paperback Series consists of selected books that have been made more accessible to consumers in an effort to increase global appeal and general circulation. With these new unabridged softcover...
متن کاملDynamic programming in constrained Markov decision processes
We consider a discounted Markov Decision Process (MDP) supplemented with the requirement that another discounted loss must not exceed a specified value, almost surely. We show that the problem can be reformulated as a standard MDP and solved using the Dynamic Programming approach. An example on a controlled queue is presented. In the last section, we briefly reinforce the connection of the Dyna...
متن کاملRisk-averse dynamic programming for Markov decision processes
We introduce the concept of a Markov risk measure and we use it to formulate risk-averse control problems for two Markov decision models: a finite horizon model and a discounted infinite horizon model. For both models we derive risk-averse dynamic programming equations and a value iteration method. For the infinite horizon problem we also develop a risk-averse policy iteration method and we pro...
متن کاملEecient Dynamic-programming Updates in Partially Observable Markov Decision Processes Eecient Dynamic-programming Updates in Partially Observable Markov Decision Processes
We examine the problem of performing exact dynamic-programming updates in partially observable Markov decision processes (pomdps) from a computational complexity viewpoint. Dynamic-programming updates are a crucial operation in a wide range of pomdp solution methods and we nd that it is intractable to perform these updates on piecewise-linear convex value functions for general pomdps. We offer ...
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: Journal of Mathematical Analysis and Applications
سال: 1980
ISSN: 0022-247X
DOI: 10.1016/0022-247x(80)90025-6