Reinforcement learning to train a cooperative network with both discrete and continuous output neurons.

Satoshi Yamada Michio Nakashima Satoru Shiono Reinforcement learning to train a cooperative network with both discrete and continuous output neurons. 1502-1508 1998 9 IEEE Transactions on Neural Networks 6 http://doi.ieeecomputersociety.org/10.1109/72.728399 db/journals/tnn/tnn9.html#YamadaNS98