On-Line Connectionist Q-Learning Produces Unreliable Performance with A Synonym Finding Task.

Ian Johnson Mark D. Plumbley

Published in: IJCNN (3) (2000)

Keyphrases

cooperative
neural network
expert systems
reinforcement learning
function approximation
multi agent
learning algorithm
state space
document retrieval
distributed representations
data sets
wordnet
query expansion
co occurrence
optimal policy
reinforcement learning algorithms
learning capabilities