Human Reinforcement Learning of Sequential Action.

George Kachergis Floris Berends Roy De Kleijn Bernhard Hommel

Published in: CogSci (2016)

Keyphrases

reinforcement learning
action selection
human subjects
partially observable domains
state space
function approximation
sensory inputs
learning process
human interaction
learning algorithm
reward shaping
human behavior
temporal difference
reinforcement learning algorithms
action space
state action
reward signal