Results 1  10
of
1,958,059
On the complexity of solving Markov decision problems
 IN PROC. OF THE ELEVENTH INTERNATIONAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE
, 1995
"... Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving MDPs and the running time of MDP solution algorithms. We argu ..."
Abstract

Cited by 159 (12 self)
 Add to MetaCart
Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving MDPs and the running time of MDP solution algorithms. We
Markov Decision Problems
 U.C. Berkeley Randomized Algorithms Class Project
, 1996
"... Markov Decision Problems (MDPs) are the foundation for many problems that are of interest to researchers in Artificial Intelligence and Operations Research. In this paper, we will review what is known about algorithms for solving MDPs as well as the complexity of solving MDPs in general. We will arg ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Markov Decision Problems (MDPs) are the foundation for many problems that are of interest to researchers in Artificial Intelligence and Operations Research. In this paper, we will review what is known about algorithms for solving MDPs as well as the complexity of solving MDPs in general. We
Linearlysolvable markov decision problems
, 2006
"... We introduce a class of Markov decision problems (MDPs) which greatly simplify Reinforcement Learning. These MDPs have discrete state spaces and continuous control spaces. The controls have the effect of scaling the transition probabilities of an underlying Markov chain. A control cost penalizing KL ..."
Abstract

Cited by 68 (15 self)
 Add to MetaCart
We introduce a class of Markov decision problems (MDPs) which greatly simplify Reinforcement Learning. These MDPs have discrete state spaces and continuous control spaces. The controls have the effect of scaling the transition probabilities of an underlying Markov chain. A control cost penalizing
Robust Solutions to Markov Decision Problems
"... Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems. ..."
Abstract
 Add to MetaCart
Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems
Reinforcement Learning Methods for ContinuousTime Markov Decision Problems
 Advances in Neural Information Processing Systems
, 1994
"... SemiMarkov Decision Problems are continuous time generalizations of discrete time Markov Decision Problems. A number of reinforcement learning algorithms have been developed recently for the solution of Markov Decision Problems, based on the ideas of asynchronous dynamic programming and stochastic ..."
Abstract

Cited by 134 (0 self)
 Add to MetaCart
SemiMarkov Decision Problems are continuous time generalizations of discrete time Markov Decision Problems. A number of reinforcement learning algorithms have been developed recently for the solution of Markov Decision Problems, based on the ideas of asynchronous dynamic programming and stochastic
A Heuristic Search Algorithm for Markov Decision Problems
, 1999
"... LAO* is a heuristic search algorithm for Markov decision problems that is derived from the classic heuristic search algorithm AO* (Hansen &; Zilberstein 1998). It shares the advantage heuristic search has over dynamic programming for simpler classes of problems: it can find optimal solutio ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
LAO* is a heuristic search algorithm for Markov decision problems that is derived from the classic heuristic search algorithm AO* (Hansen &; Zilberstein 1998). It shares the advantage heuristic search has over dynamic programming for simpler classes of problems: it can find optimal
Markov Decision Problems where Means bound Variances
"... We identify a rich class of finitehorizon Markov decision problems (MDPs) for which the variance of the optimal total reward can be bounded by a simple affine function of its expected value. The class is characterized by three natural properties: reward boundedness, existence of a donothing action ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
We identify a rich class of finitehorizon Markov decision problems (MDPs) for which the variance of the optimal total reward can be bounded by a simple affine function of its expected value. The class is characterized by three natural properties: reward boundedness, existence of a do
Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
 Advances in Neural Information Processing Systems 7
, 1995
"... Increasing attention has been paid to reinforcement learning algorithms in recent years, partly due to successes in the theoretical analysis of their behavior in Markov environments. If the Markov assumption is removed, however, neither generally the algorithms nor the analyses continue to be usable ..."
Abstract

Cited by 171 (7 self)
 Add to MetaCart
to be usable. We propose and analyze a new learning algorithm to solve a certain class of nonMarkov decision problems. Our algorithm applies to problems in which the environment is Markov, but the learner has restricted access to state information. The algorithm involves a MonteCarlo policy evaluation
Variable Independence in Markov Decision Problems
"... In decisiontheoretic planning, the problem of planning under uncertainty is formulated as a multidimensional, or factored MDP. Traditional dynamic programming techniques are ine cient for solving factored MDPs whose state and action spaces are exponential in the number of the state and action varia ..."
Abstract
 Add to MetaCart
In decisiontheoretic planning, the problem of planning under uncertainty is formulated as a multidimensional, or factored MDP. Traditional dynamic programming techniques are ine cient for solving factored MDPs whose state and action spaces are exponential in the number of the state and action
Robustness in markov decision problems with uncertain transition matrices
 In NIPS
, 2004
"... Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems. We ..."
Abstract

Cited by 30 (0 self)
 Add to MetaCart
Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems
Results 1  10
of
1,958,059