On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
نویسندگان
چکیده
Previous work on planning as active inference addresses finite horizon problems and solutions valid for online planning. We propose solving the general Stochastic Shortest-Path Markov Decision Process (SSP MDP) probabilistic inference. Furthermore, we discuss offline methods under uncertainty. In an SSP MDP, is indefinite unknown a priori. MDPs generalize infinite are widely used in artificial intelligence community. Additionally, highlight some of differences between MDP using dynamic programming approaches community F
منابع مشابه
Shortest Path Based Decision Making Using Probabilistic Inference
We present a new perspective on the classical shortest path routing (SPR) problem in graphs. We show that the SPR problem can be recast to that of probabilistic inference in a mixture of simple Bayesian networks. Maximizing the likelihood in this mixture becomes equivalent to solving the SPR problem. We develop the well known Expectation-Maximization (EM) algorithm for the SPR problem that maxi...
متن کاملSolving Stochastic Shortest-Path Problems with RTDP
We present a modification of the Real-Time Dynamic Programming (rtdp) algorithm that makes it a genuine off-line algorithm for solving Stochastic Shortest-Path problems. Also, a new domainindependent and admissible heuristic is presented for Stochastic Shortest-Path problems. The new algorithm and heuristic are compared with Value Iteration over benchmark problems with large state spaces. The r...
متن کاملParallel Algorithms for Solving Markov Decision Process
Markov decision process (MDP) provides the foundations for a number of problems, such as artificial intelligence studying, automated planning and reinforcement learning. MDP can be solved efficiently in theory. However, for large scenarios, more investigations are needed to reveal practical algorithms. Algorithms for solving MDP have a natural concurrency. In this paper, we present parallel alg...
متن کاملStochastic Shortest Path Games
We consider dynamic, two-player, zero-sum games where the \minimizing" player seeks to drive an underlying nite-state dynamic system to a special terminal state along a least expected cost path. The \maximizer" seeks to interfere with the minimizer's progress so as to maximize the expected total cost. We consider, for the rst time, undiscounted nite-state problems, with compact action spaces, a...
متن کاملOn Solving the Quadratic Shortest Path Problem
The quadratic shortest path problem is the problem of finding a path in a directed graph such that the sum of interaction costs over all pairs of arcs on the path is minimized. We derive several semidefinite programming relaxations for the quadratic shortest path problem with a matrix variable of order m + 1, where m is the number of arcs in the graph. We use the alternating direction method of...
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: Communications in computer and information science
سال: 2021
ISSN: ['1865-0937', '1865-0929']
DOI: https://doi.org/10.1007/978-3-030-93736-2_58