Performance improvement of evolution strategies using reinforcement learning
- Authors
- Lee, Sang-Hwan; Jun, Hyo-Byung; Sim, Kwee-Bo
- Issue Date
- Aug-1999
- Publisher
- IEEE, Piscataway, NJ, United States
- Citation
- IEEE International Conference on Fuzzy Systems, v.2, pp II - 639 - II-644
- Journal Title
- IEEE International Conference on Fuzzy Systems
- Volume
- 2
- Start Page
- II
- End Page
- 639 - II-644
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/56566
- ISSN
- 0000-0000
- Abstract
- In this paper, we propose a new type of evolution strategies combined with reinforcement learning. We use the change of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length of mutation. With this proposed method, the convergence rate is improved. Also, we use Cauchy distributed mutation to increase global convergence faculty. Cauchy distributed mutation is more likely to escape from a local minimum or move away from a plateau than Gaussian distributed mutation. After an outline of the history of evolution strategies, we will explain the evolution strategies combined with the reinforcement learning, that is reinforcement evolution strategies. The performance of proposed method will be estimated by comparison with conventional evolution strategies on several test problems.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of ICT Engineering > School of Electrical and Electronics Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.