Sciweavers

38 search results - page 4 / 8
» Risk-sensitive planning in partially observable environments
Sort
View
AIPS
2008
13 years 8 months ago
Multiagent Planning Under Uncertainty with Stochastic Communication Delays
We consider the problem of cooperative multiagent planning under uncertainty, formalized as a decentralized partially observable Markov decision process (Dec-POMDP). Unfortunately...
Matthijs T. J. Spaan, Frans A. Oliehoek, Nikos A. ...
AAAI
2007
13 years 8 months ago
Situated Conversational Agents
A Situated Conversational Agent (SCA) is an agent that engages in dialog about the context within which it is embedded. Situated dialog is characterized by its deep connection to ...
William Thompson
ISRR
2005
Springer
163views Robotics» more  ISRR 2005»
13 years 11 months ago
POMDP Planning for Robust Robot Control
POMDPs provide a rich framework for planning and control in partially observable domains. Recent new algorithms have greatly improved the scalability of POMDPs, to the point where...
Joelle Pineau, Geoffrey J. Gordon
ATAL
2006
Springer
13 years 9 months ago
Decentralized planning under uncertainty for teams of communicating agents
Decentralized partially observable Markov decision processes (DEC-POMDPs) form a general framework for planning for groups of cooperating agents that inhabit a stochastic and part...
Matthijs T. J. Spaan, Geoffrey J. Gordon, Nikos A....
ATAL
2010
Springer
13 years 6 months ago
Closing the learning-planning loop with predictive state representations
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
Byron Boots, Sajid M. Siddiqi, Geoffrey J. Gordon