Reactive Navigation Using Reinforment Learning in Situations of POMDPs.

Paolo Puliti Guido Tascini Anna Montesanto

Published in: IWANN (2) (2001)

Keyphrases

learning algorithm
learning systems
reinforcement learning
learning process
learning tasks
neural network
supervised learning
machine learning
online learning
knowledge acquisition
unsupervised learning
learning problems
decision trees
search algorithm
background knowledge
partially observable