656 search results - page 9 / 132 » Complexity of finite-horizon Markov decision process problem... |
104
Voted
FLAIRS
1998
15 years 3 months ago
1998
Reinforcement learning (RL) problems constitute an important class of learning and control problems faced by artificial intelligence systems. In these problems, one is faced with ...
113
click to vote
MOR
2007
15 years 1 months ago
2007
We consider the problem of solving a nonhomogeneous infinite horizon Markov Decision Process (MDP) problem in the general case of potentially multiple optimal first period polic...
162
click to vote
AIPS
2011
14 years 5 months ago
2011
In this paper, we present a new algorithm that integrates recent advances in solving continuous bandit problems with sample-based rollout methods for planning in Markov Decision P...
115
Voted
AAAI
1998
15 years 3 months ago
1998
We present a technique for computing approximately optimal solutions to stochastic resource allocation problems modeled as Markov decision processes (MDPs). We exploit two key pro...
104
click to vote
ECML
2005
Springer
15 years 7 months ago
2005
Springer
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...