TY - JOUR
T1 - A phased reinforcement learning algorithm for complex control problems
AU - Goto, Takakuni
AU - Homma, Noriyasu
AU - Yoshizawa, Makoto
AU - Abe, Kenichi
PY - 2007/7
Y1 - 2007/7
N2 - In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.
AB - In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.
KW - Human exploration-exploitation strategy
KW - Promising zone
KW - Reinforcement learning
KW - Shaping function
UR - http://www.scopus.com/inward/record.url?scp=34547938723&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34547938723&partnerID=8YFLogxK
U2 - 10.1007/s10015-007-0427-y
DO - 10.1007/s10015-007-0427-y
M3 - Article
AN - SCOPUS:34547938723
SN - 1433-5298
VL - 11
SP - 190
EP - 196
JO - Artificial Life and Robotics
JF - Artificial Life and Robotics
IS - 2
ER -