Reward is enough.

David Silver Satinder P. Singh Doina Precup Richard S. Sutton

Published in: Artif. Intell. (2021)

Keyphrases

reinforcement learning
long run
average reward
cooperative
reward function
scheduling problem
control system
multi armed bandit
inverse reinforcement learning
medical images
least squares
neural network
learning process
expert systems
search algorithm
search engine
learning algorithm
data mining