1. Adaptive scheduling strategy in knowledgeable manufacturing system based on SAUBQ-learning.
- Author
-
WANG Hao-xiang and YAN Hong-sen
- Subjects
- *
SCHEDULING , *REINFORCEMENT learning , *MANUFACTURING processes , *HEURISTIC , *LEARNING classifier systems - Abstract
An adaptive scheduling strategy based on state-action uncertainty bias based Q-learning (SAUBQ-learning) is proposed for adaptive scheduling in knowledgeable manufacturing environment. Aiming at the problem of slow convergence and long training time in conventional Q-learning process, a state-action uncertainty measure is defined by information entropy, on the basis of which a Q-learning action bias information function is defined. The bias information is integrated into Q-learning system by designing heuristic Q-learning reward function, and the optimal strategy invariance and convergence of SAUBQ-learning are proved. In learning process, search space is adjusted by bias information, the effective state-action number explored by Q-learning is reduced. Furthermore, the bias information is also continually updated by Q-learning results, and misleading Q-learning process is avoided. Simulation experiment results indicate that the strategy has better adaptive feature in dynamic environment and the feature of converging quickly in large state space, and improves the efficiency of scheduling. [ABSTRACT FROM AUTHOR]
- Published
- 2014