Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective.

Tom Everitt Marcus Hutter

Published in: CoRR (2019)

Keyphrases

reinforcement learning
influence diagrams
decision problems
sequential decision making
machine learning
bayesian networks
graphical models
function approximation
search algorithm
training set
probabilistic inference
partially observable
action space
decision making under uncertainty