Sciweavers

3491 search results - page 270 / 699
» Cascaded Markov Models
Sort
View
NMR
2004
Springer
16 years 3 days ago
Probabilistic reasoning in dynamic multiagent systems
Probabilistic reasoning with multiply sectioned Bayesian networks (MSBNs) has been successfully applied in static domains under the cooperative multiagent paradigm. Probabilistic ...
Xiangdong An, Yang Xiang, Nick Cercone
SIGECOM
2003
ACM
134views ECommerce» more  SIGECOM 2003»
16 years 5 hour ago
Correlated equilibria in graphical games
We examine correlated equilibria in the recently introduced formalism of graphical games, a succinct representation for multiplayer games. We establish a natural and powerful rela...
Sham Kakade, Michael J. Kearns, John Langford, Lui...
COLT
1994
Springer
15 years 11 months ago
Learning Probabilistic Automata with Variable Memory Length
We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic nite automata...
Dana Ron, Yoram Singer, Naftali Tishby
UAI
2000
15 years 8 months ago
PEGASUS: A policy search method for large MDPs and POMDPs
We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a mo...
Andrew Y. Ng, Michael I. Jordan
CORR
2010
Springer
105views Education» more  CORR 2010»
15 years 5 months ago
Optimism in Reinforcement Learning Based on Kullback-Leibler Divergence
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
Sarah Filippi, Olivier Cappé, Aurelien Gari...