Efficient solutions to factored MDPs with imprecise transition probabilities
نویسندگان
چکیده
منابع مشابه
Efficient Solutions to Factored MDPs with Imprecise Transition Probabilities
When modeling real-world decision-theoretic planning problems in the Markov Decision Process (MDP) framework, it is often impossible to obtain a completely accurate estimate of transition probabilities. For example, natural uncertainty arises in the transition specification due to elicitation of MDP transition models from an expert or estimation from data, or non-stationary transition distribut...
متن کاملFactored Markov decision processes with Imprecise Transition Probabilities
This paper presents a short survey of the research we have carried out on planning under uncertainty where we consider different forms of imprecision on the probability transition functions. Our main results are on efficient solutions for Markov Decision Process with Imprecise Transition Probabilities (MDP-IPs), a generalization of a Markov Decision Process where the imprecise probabilities are...
متن کاملRepresenting and Solving Factored Markov Decision Processes with Imprecise Probabilities
This paper investigates Factored Markov Decision Processes with Imprecise Probabilities; that is, Markov Decision Processes where transition probabilities are imprecisely specified, and where their specification does not deal directly with states, but rather with factored representations of states. We first define a Factored MDPIP, based on a multilinear formulation for MDPIPs; then we propose ...
متن کاملFactored Markov Decision Processes with Imprecise Probabilities: a multilinear solution
There are efficient solutions to planning problems modeled as a Markov Decision Process (MDP) envolving a reasonable number of states. However, known extensions of MDP are more suited to represent practical and more interesting applications, such as: (i) an MDP where states are represented by state variables, called a factored MDP; (ii) an MDP where probabilities are not completely known, calle...
متن کاملSample Efficient Feature Selection for Factored MDPs
In reinforcement learning, the state of the real world is often represented by feature vectors. However, not all of the features may be pertinent for solving the current task. We propose Feature Selection Explore and Exploit (FS-EE), an algorithm that automatically selects the necessary features while learning a Factored Markov Decision Process, and prove that under mild assumptions, its sample...
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: Artificial Intelligence
سال: 2011
ISSN: 0004-3702
DOI: 10.1016/j.artint.2011.01.001