Achievements, Motivations and Rewards in Faunasphere.

Jason Begy Mia Consalvo

Published in: Game Stud. (2011)

Keyphrases

reinforcement learning
multiarmed bandit
bandit problems
markov decision processes
multi armed bandits
credit assignment
reward function
long term and short term
cooperative
hidden markov models
control policy
neural network
computer vision
computational complexity
online learning
long run