Maximum reward reinforcement learning: A non-cumulative reward criterion

K.H. Quah، نويسنده , , Chai Quek، نويسنده ,

روزنامه با شماره پیاپی سال 2006

9

351

359

reinforcement learning , Maximum reward , FITSK-RL , Optimal stopping problem , Two-cycletask , Maximum reward-oriented behaviour , Financial derivative pricing , Non-cumulative reward

Expert Systems with Applications

2006

Expert Systems with Applications

198449