Sciweavers

127 search results - page 4 / 26
» Decentralized Bisimulation for Multiagent Systems
Sort
View
CDC
2008
IEEE
144views Control Systems» more  CDC 2008»
13 years 9 months ago
Controllability decompositions of networked systems through quotient graphs
In this paper we study decentralized, networked systems whose interaction dynamics are given by a nearestneighbor averaging rule. By letting one node in the network take on the rol...
Simone Martini, Magnus Egerstedt, Antonio Bicchi
AI
2011
Springer
12 years 11 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
IROS
2007
IEEE
132views Robotics» more  IROS 2007»
14 years 1 months ago
Hysteretic q-learning : an algorithm for decentralized reinforcement learning in cooperative multi-agent teams
— Multi-agent systems (MAS) are a field of study of growing interest in a variety of domains such as robotics or distributed controls. The article focuses on decentralized reinf...
Laëtitia Matignon, Guillaume J. Laurent, Nadi...
ATAL
2003
Springer
14 years 24 days ago
Transition-independent decentralized markov decision processes
There has been substantial progress with formal models for sequential decision making by individual agents using the Markov decision process (MDP). However, similar treatment of m...
Raphen Becker, Shlomo Zilberstein, Victor R. Lesse...
ATAL
2010
Springer
13 years 8 months ago
Point-based backup for decentralized POMDPs: complexity and new algorithms
Decentralized POMDPs provide an expressive framework for sequential multi-agent decision making. Despite their high complexity, there has been significant progress in scaling up e...
Akshat Kumar, Shlomo Zilberstein