15 search results - page 3 / 3 » Incremental plan aggregation for generating policies in MDPs |
CORR
2012
Springer
12 years 22 days ago
2012
Springer
Abstract— In this paper, we consider a class of continuoustime, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation ...
NIPS
1998
13 years 6 months ago
1998
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
ATAL
2009
Springer
13 years 11 months ago
2009
Springer
Decentralized partially observable MDPs (DEC-POMDPs) provide a rich framework for modeling decision making by a team of agents. Despite rapid progress in this area, the limited sc...
ATAL
2009
Springer
13 years 11 months ago
2009
Springer
Recent scaling up of decentralized partially observable Markov decision process (DEC-POMDP) solvers towards realistic applications is mainly due to approximate methods. Of this fa...
UAI
2008
13 years 6 months ago
2008
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...