Solving factored MDPs using non-homogeneous partitions
نویسندگان
چکیده
منابع مشابه
Solving factored MDPs using non-homogeneous partitions
We present an algorithm for aggregating states in solving large MDPs (represented as factored MDPs) using search by successive re nement in the space of nonhomogeneous partitions. Homogeneity is de ned in terms of stochastic bisimulation and reward equivalence within blocks of a partition. Since homogeneous partitions that de ne equivalent reduced-state-space MDPs can have a large number of blo...
متن کاملSolving Factored MDPs via Non-Homogeneous Partitioning
This paper describes an algorithm for solving large state-space MDPs (represented as factored MDPs) using search by successive refinement in the space of non-homogeneous partitions. Homogeneity is defined in terms of bisimulation and reward equivalence within blocks of a partition. Since homogeneous partitions that define equivalent reduced state-space MDPs can have a large number of blocks, we...
متن کاملApproximate Linear Programming for Solving Hybrid Factored MDPs
Hybrid approximate linear programming (HALP) has recently emerged as a promising approach to solving large factored Markov decision processes (MDPs) with discrete and continuous state and action variables. Its central idea is to reformulate initially intractable problem of computing the optimal value function as its linear programming approximation. In this work, we present the HALP framework a...
متن کاملAn MCMC Approach to Solving Hybrid Factored MDPs
Hybrid approximate linear programming (HALP) has recently emerged as a promising framework for solving large factored Markov decision processes (MDPs) with discrete and continuous state and action variables. Our work addresses its major computational bottleneck – constraint satisfaction in large structured domains of discrete and continuous variables. We analyze this problem and propose a novel...
متن کاملSolving Factored MDPs with Hybrid State and Action Variables
Efficient representations and solutions for large decision problems with continuous and discrete variables are among the most important challenges faced by the designers of automated decision support systems. In this paper, we describe a novel hybrid factored Markov decision process (MDP) model that allows for a compact representation of these problems, and a new hybrid approximate linear progr...
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: 2003
ISSN: 0004-3702
DOI: 10.1016/s0004-3702(02)00377-6