A pulse neural network reinforcement learning algorithm for partially observable Markov decision processes.

Koichiro Takita Masafumi Hagiwara A pulse neural network reinforcement learning algorithm for partially observable Markov decision processes. 42-52 2005 36 Systems and Computers in Japan 3 http://dx.doi.org/10.1002/scj.10645 db/journals/scjapan/scjapan36.html#TakitaH05