Sciweavers

683 search results - page 57 / 137
» Coarticulation in Markov Decision Processes
Sort
View
ATAL
2011
Springer
12 years 10 months ago
Towards a unifying characterization for quantifying weak coupling in dec-POMDPs
Researchers in the field of multiagent sequential decision making have commonly used the terms “weakly-coupled” and “loosely-coupled” to qualitatively classify problems i...
Stefan J. Witwicki, Edmund H. Durfee
ICML
2008
IEEE
14 years 11 months ago
Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Finale Doshi, Joelle Pineau, Nicholas Roy
ICALP
2009
Springer
14 years 10 months ago
Reachability in Stochastic Timed Games
We define stochastic timed games, which extend two-player timed games with probabilities (following a recent approach by Baier et al), and which extend in a natural way continuous-...
Patricia Bouyer, Vojtech Forejt
ECML
2007
Springer
14 years 4 months ago
Safe Q-Learning on Complete History Spaces
In this article, we present an idea for solving deterministic partially observable markov decision processes (POMDPs) based on a history space containing sequences of past observat...
Stephan Timmer, Martin Riedmiller
GECCO
2004
Springer
142views Optimization» more  GECCO 2004»
14 years 3 months ago
Improving MACS Thanks to a Comparison with 2TBNs
Abstract. Factored Markov Decision Processes is the theoretical framework underlying multi-step Learning Classifier Systems research. This framework is mostly used in the context ...
Olivier Sigaud, Thierry Gourdin, Pierre-Henri Wuil...