Quasi deterministic POMDPs and DecPOMDPs.

Camille Besse Brahim Chaib-draa

Published in: AAMAS (2010)

Keyphrases

reinforcement learning
partially observable markov decision processes
belief state
stochastic domains
artificial intelligence
information systems
case study
markov decision processes
black box
real time
databases
dynamic programming
finite state
partially observable
distributed constraint optimization