Login / Signup
Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies.
Seiji Ishihara
Harukazu Igarashi
Published in:
PRICAI (2008)
Keyphrases
</>
gradient method
learning algorithm
actor critic
policy gradient
policy gradient methods
selective perception
cost function
optimal policy
step size
clustering method
cellular automaton
machine learning
image classification
natural language processing
search space
reinforcement learning
information retrieval