Axioms for Rational Reinforcement Learning.

Peter Sunehag Marcus Hutter

Published in: ALT (2011)

Keyphrases

reinforcement learning
profit sharing
function approximation
decision making
learning algorithm
knowledge base
model free

multi agent
machine learning
state space
supervised learning
reinforcement learning algorithms
temporal difference
optimal policy

stochastic approximation
temporal difference learning
dynamic programming
case study
neural network
first order logic
action selection

real time
learning agent
action space
function approximators
learning process
policy search