An Axiomatic Approach to Block Rewards.

Xi Chen Christos H. Papadimitriou Tim Roughgarden

Published in: AFT (2019)

Keyphrases

reinforcement learning
credit assignment
database
data sets
e learning
quadtree decomposition
real time
genetic algorithm
information systems
markov decision processes
reward function
image blocks
block wise
bandit problems
multiarmed bandit