On the locality of action domination in sequential decision making.

Emmanuel Rachelson Michail G. Lagoudakis

Published in: ISAIM (2010)

Keyphrases

sequential decision making
reinforcement learning
decision problems
influence diagrams
interactive dynamic influence diagrams
temporal difference
action selection
decision making
special case
optimal strategy
optimal policy
neural network
active learning
probabilistic model
sensitivity analysis
expected utility