Experimental study of the eligibility traces in complex valued reinforcement learning

被引：0

作者：

Shibuya, Takeshi ^{[1
]}

Shimada, Shingo ^{[1
]}

Harnagarni, Tomoki ^{[1
]}

机构：

[1] Yokohama Natl Univ, Grad Sch Engn, Yokohama, Kanagawa, Japan

来源：

2007 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-8 | 2007年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Effectiveness of eligibility traces in complex valued reinforcement learning is studied. Complex valued reinforcement learning is a new method inspired by complex valued nerual networks. In this study, it is desired that various approaches in the ordinally real valued reinforcement learning are applied to the complex valued reinforcement learning. This paper focuses attention on an experimental study of the eligibility traces. Simulation results infer that there is a possibility of overcoming tight perceptual aliasing with long trace back up.

引用

页码：2458 / 2463

页数：6

共 50 条

[1] Reinforcement learning with replacing eligibility traces
Singh, SP
Sutton, RS
MACHINE LEARNING, 1996, 22 (1-3) : 123 - 158
[2] Adaptive Eligibility Traces for Online Deep Reinforcement Learning
Kobayashi, Taisuke
INTELLIGENT AUTONOMOUS SYSTEMS 16, IAS-16, 2022, 412 : 417 - 428
[3] Reinforcement learning with goal-directed eligibility traces
Andrecut, M
Ali, MK
INTERNATIONAL JOURNAL OF MODERN PHYSICS C, 2004, 15 (09): : 1235 - 1247
[4] A comparison of reinforcement learning with eligibility traces and integrated learning, planning and reacting
Pérez-Uribe, A
Sanchez, E
COMPUTATIONAL INTELLIGENCE FOR MODELLING, CONTROL & AUTOMATION - NEURAL NETWORKS & ADVANCED CONTROL STRATEGIES, 1999, 54 : 154 - 159
[5] Efficient ant reinforcement learning using replacing eligibility traces
Lee, SeungGwan
Hong, SeokMi
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2006, PROCEEDINGS, 2006, 4029 : 823 - 832
[6] On the efficient implementation biologic reinforcement learning using eligibility traces
Lee, SeungGwan
ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 476 - 481
[7] Community energy storage operation via reinforcement learning with eligibility traces
Duque, Edgar Mauricio Salazar
Giraldo, Juan S.
Vergara, Pedro P.
Nguyen, Phuong
van der Molen, Anne
Slootweg, Han
ELECTRIC POWER SYSTEMS RESEARCH, 2022, 212
[8] Complex-valued reinforcement learning
Hamagami, Tornoki
Shibuya, Takashi
Shimada, Shingo
2006 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-6, PROCEEDINGS, 2006, : 4175 - +
[9] Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
Daley, Brett
White, Martha
Amato, Christopher
Machado, Marlos C.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202
[10] Adaptive Fuzzy Watkins: A New Adaptive Approach for Eligibility Traces in Reinforcement Learning
Shokri, Matin
Khasteh, Seyed Hossein
Aminifar, Amin
INTERNATIONAL JOURNAL OF FUZZY SYSTEMS, 2019, 21 (05) : 1443 - 1454

← 1 2 3 4 5 →