A Performance Bound for Model Based Online Reinforcement Learning.

Lukas Beckenbach Stefan Streif

Published in: CoRR (2021)

Keyphrases

reinforcement learning
model free
online learning
upper bound
lower bound
error bounds
multi agent
real time
worst case
state space
balancing exploration and exploitation
cross cultural
function approximation
decision making
machine learning
learning algorithm
genetic algorithm
data mining