Sciweavers

64 search results - page 3 / 13
» A dynamic programming algorithm for decentralized Markov dec...
Sort
View
AAAI
2012
11 years 7 months ago
Planning in Factored Action Spaces with Symbolic Dynamic Programming
We consider symbolic dynamic programming (SDP) for solving Markov Decision Processes (MDP) with factored state and action spaces, where both states and actions are described by se...
Aswin Raghavan, Saket Joshi, Alan Fern, Prasad Tad...
AAAI
2008
13 years 7 months ago
Interaction Structure and Dimensionality Reduction in Decentralized MDPs
Decentralized Markov Decision Processes are a powerful general model of decentralized, cooperative multi-agent problem solving. The high complexity of the general problem leads to...
Martin Allen, Marek Petrik, Shlomo Zilberstein
ATAL
2010
Springer
13 years 9 days ago
Approximate dynamic programming with affine ADDs
The Affine ADD (AADD) is an extension of the Algebraic Decision Diagram (ADD) that compactly represents context-specific, additive and multiplicative structure in functions from a...
Scott Sanner, William T. B. Uther, Karina Valdivia...
IJCAI
2007
13 years 6 months ago
First Order Decision Diagrams for Relational MDPs
Dynamic programming algorithms provide a basic tool identifying optimal solutions in Markov Decision Processes (MDP). The paper develops a representation for decision diagrams sui...
Chenggang Wang, Saket Joshi, Roni Khardon
AI
2011
Springer
12 years 9 months ago
Decentralized MDPs with sparse interactions
In this work, we explore how local interactions can simplify the process of decision-making in multiagent systems, particularly in multirobot problems. We review a recent decision-...
Francisco S. Melo, Manuela M. Veloso