An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function.

Hajime Kimura Shigenobu Kobayashi An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function. 278-286 1998 conf/icml/1998 ICML db/conf/icml/icml1998.html#KimuraK98