Reinforcement learning for discounted values often loses the goal in the application to animal learning.

Yoshiya Yamaguchi Yutaka Sakai

Published in: Neural Networks (2012)

Keyphrases

reinforcement learning
learning process
learning problems
learning algorithm
learning tasks
online learning
markov decision processes
supervised learning
unsupervised learning
learning systems
actor critic
evolutionary learning
agent learns
data sets
optimal control
optimal policy
prior knowledge
multi agent