Abstract
A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.
| Original language | English |
|---|---|
| Title of host publication | 2006 IEEE Congress on Evolutionary Computation, CEC 2006 |
| Pages | 1537-1543 |
| Number of pages | 7 |
| Publication status | Published - 2006 |
| Event | 2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC Duration: 2006 Jul 16 → 2006 Jul 21 |
Other
| Other | 2006 IEEE Congress on Evolutionary Computation, CEC 2006 |
|---|---|
| City | Vancouver, BC |
| Period | 06/7/16 → 06/7/21 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Theoretical Computer Science
Cite this
An extension of genetic network programming with reinforcement learning using actor-critic. / Hatakeyama, Hiroyuki; Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki.
2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1537-1543 1688491.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - An extension of genetic network programming with reinforcement learning using actor-critic
AU - Hatakeyama, Hiroyuki
AU - Mabu, Shingo
AU - Hirasawa, Kotaro
AU - Furuzuki, Takayuki
PY - 2006
Y1 - 2006
N2 - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.
AB - A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.
UR - http://www.scopus.com/inward/record.url?scp=34547365679&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34547365679&partnerID=8YFLogxK
M3 - Conference contribution
SN - 0780394879
SN - 9780780394872
SP - 1537
EP - 1543
BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006
ER -