An Adaptive Implementation of ε-Greedy in Reinforcement Learning.

Alexandre dos Santos Mignon Ricardo Luis de Azevedo da Rocha

Published in: ANT/SEIT (2017)

Keyphrases

reinforcement learning
greedy algorithm
function approximation
markov decision processes
databases
database
model free
multi agent
learning process
implementation details
temporal difference
transfer learning
optimal policy
state space
expert systems
multiscale
decision making
feature selection
real world
real time