Optimal Tuning of Continual Online Exploration in Reinforcement Learning.

Youssef Achbany François Fouss Luh Yen Alain Pirotte Marco Saerens

Published in: ICANN (1) (2006)

Keyphrases

reinforcement learning
online learning
dynamic programming
balancing exploration and exploitation
optimal control
real time
closed form
active exploration
optimal design
worst case
state space
exploration exploitation tradeoff
online communities
database
optimal strategy
fine tuning
multi agent