TY - GEN
T1 - Research of a parallel learning adaptive dynamic programming based on genetic algorithms
AU - Wang, Zhenyu
AU - Dai, Yaping
AU - Yao, Yuan
PY - 2010
Y1 - 2010
N2 - In adaptive dynamic programming (ADP), the utility function is always completely designed by experience which cannot evaluate system cost very well. A novel adaptive dynamic programming based on genetic algorithms (GAADP) method is proposed with global searching and fast learning speed. First, a normal utility function of ADP was designed according to the error between current states and expected values. Second, genetic algorithms (GAs) were used to search for the optimal parameters of utility function in ADP. Finally, we employed GAADP on an inverted pendulum system control. The simulation experiments indicated that GAADP method can increase the learning speed and easily achieve the balancing state. The learning speed doubled than general ADP method, meanwhile the control performance of successful trials also improved.
AB - In adaptive dynamic programming (ADP), the utility function is always completely designed by experience which cannot evaluate system cost very well. A novel adaptive dynamic programming based on genetic algorithms (GAADP) method is proposed with global searching and fast learning speed. First, a normal utility function of ADP was designed according to the error between current states and expected values. Second, genetic algorithms (GAs) were used to search for the optimal parameters of utility function in ADP. Finally, we employed GAADP on an inverted pendulum system control. The simulation experiments indicated that GAADP method can increase the learning speed and easily achieve the balancing state. The learning speed doubled than general ADP method, meanwhile the control performance of successful trials also improved.
KW - Adaptive dynamic programming
KW - Genetic algorithms
KW - Inverted pendulum control
KW - Utility function
UR - https://www.scopus.com/pages/publications/78649250176
U2 - 10.1109/ICCSNA.2010.5588740
DO - 10.1109/ICCSNA.2010.5588740
M3 - Conference contribution
AN - SCOPUS:78649250176
SN - 9781424474769
T3 - 2010 2nd International Conference on Communication Systems, Networks and Applications, ICCSNA 2010
SP - 350
EP - 353
BT - 2010 2nd International Conference on Communication Systems, Networks and Applications, ICCSNA 2010
T2 - 2010 2nd International Conference on Communication Systems, Networks and Applications, ICCSNA 2010
Y2 - 29 June 2010 through 1 July 2010
ER -