TY - JOUR

T1 - A parallel fuzzy inference model with distributed prediction scheme for reinforcement learning

AU - Kuo, Yau Hwang

AU - Hsu, Jang Pong

AU - Wang, Cheng Wen

PY - 1998

Y1 - 1998

N2 - This paper proposes a three-layered parallel fuzzy inference model called reinforcement fuzzy neural network with distributed prediction scheme (RFNN-DPS), which performs reinforcement learning with a novel distributed prediction scheme. In RFNN-DPS, an additional predictor for predicting the external reinforcement signal is not necessary, and the internal reinforcement information is distributed into fuzzy rules (rule nodes). Therefore, using RFNN-DPS, only one network is needed to construct a fuzzy logic system with the abilities of parallel inference and reinforcement learning. Basically, the information for prediction in RFNN-DPS is composed of credit values stored in fuzzy rule nodes, where each node holds a credit vector to represent the reliability of the corresponding fuzzy rule. The credit values are not only accessed for predicting external reinforcement signals, but also provide a more profitable internal reinforcement signal to each fuzzy rule itself. RFNN-DPS performs a credit-based exploratory algorithm to adjust its internal status according to the internal reinforcement signal. During learning, the RFNN-DPS network is constructed by a single-step or multistep reinforcement learning algorithm based on the ART concept. According to our experimental results, RFNN-DPS shows the advantages of simple network structure, fast learning speed, and explicit representation of rule reliability.

AB - This paper proposes a three-layered parallel fuzzy inference model called reinforcement fuzzy neural network with distributed prediction scheme (RFNN-DPS), which performs reinforcement learning with a novel distributed prediction scheme. In RFNN-DPS, an additional predictor for predicting the external reinforcement signal is not necessary, and the internal reinforcement information is distributed into fuzzy rules (rule nodes). Therefore, using RFNN-DPS, only one network is needed to construct a fuzzy logic system with the abilities of parallel inference and reinforcement learning. Basically, the information for prediction in RFNN-DPS is composed of credit values stored in fuzzy rule nodes, where each node holds a credit vector to represent the reliability of the corresponding fuzzy rule. The credit values are not only accessed for predicting external reinforcement signals, but also provide a more profitable internal reinforcement signal to each fuzzy rule itself. RFNN-DPS performs a credit-based exploratory algorithm to adjust its internal status according to the internal reinforcement signal. During learning, the RFNN-DPS network is constructed by a single-step or multistep reinforcement learning algorithm based on the ART concept. According to our experimental results, RFNN-DPS shows the advantages of simple network structure, fast learning speed, and explicit representation of rule reliability.

UR - http://www.scopus.com/inward/record.url?scp=0003371120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0003371120&partnerID=8YFLogxK

U2 - 10.1109/3477.662757

DO - 10.1109/3477.662757

M3 - Article

C2 - 18255934

AN - SCOPUS:0003371120

SN - 1083-4419

VL - 28

SP - 160

EP - 172

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 2

ER -