Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness to the E<sup>3</sup> Algorithm.

Carlos Domingo Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness to the E<sup>3</sup> Algorithm. 241-251 http://link.springer.de/link/service/series/0558/bibs/1501/15010241.htm http://link.springer.de/link/service/series/0558/bibs/1720/17200241.htm 1999 conf/alt/1999 ATL db/conf/alt/alt1999.html#Domingo98