From Fly Detectors to Action Control: Representations in Reinforcement Learning

被引：0

作者：

Rusanen, Anna-Mari ^{[1
]}

Lappi, Otto ^{[1
]}

Pekkanen, Jami ^{[1
]}

Kuokkanen, Jesse ^{[1
]}

机构：

[1] Univ Helsinki, POB 24, Helsinki 00014, Finland

来源：

PHILOSOPHY OF SCIENCE | 2021年 / 88卷 / 05期

关键词：

RECEPTIVE FIELDS; MOTOR CONTROL; MODELS;

D O I：

10.1086/715513

中图分类号：

N09 [自然科学史]; B [哲学、宗教];

学科分类号：

01 ; 0101 ; 010108 ; 060207 ; 060305 ; 0712 ;

摘要：

According to radical enactivists, cognitive sciences should abandon the representational framework. Perceptuomotor cognition and action control are often provided as paradigmatic examples of nonrepresentational cognitive phenomena. In this article, we illustrate how motor and action control are studied in research that uses reinforcement learning algorithms. Crucially, this approach can be given a representational interpretation. Hence, reinforcement learning provides a way to explicate action-oriented views of cognitive systems in a representational way.

引用

页码：1045 / 1054

页数：10

共 50 条

[1] Learning Action Representations for Reinforcement Learning
Chandak, Yash
Theocharous, Georgios
Kostas, James E.
Jordan, Scott M.
Thomas, Philip S.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[2] Action control, forward models and expected rewards: representations in reinforcement learning
Rusanen, Anna-Mari
Lappi, Otto
Kuokkanen, Jesse
Pekkanen, Jami
SYNTHESE, 2021, 199 (5-6) : 14017 - 14033
[3] Action control, forward models and expected rewards: representations in reinforcement learning
Anna-Mari Rusanen
Otto Lappi
Jesse Kuokkanen
Jami Pekkanen
Synthese, 2021, 199 : 14017 - 14033
[4] The use of continuous action representations to scale deep reinforcement learning for inventory control
Vanvuchelen, Nathalie
De Moor, Bram J.
Boute, Robert N.
IMA JOURNAL OF MANAGEMENT MATHEMATICS, 2024, 36 (01) : 51 - 66
[5] The Utility of Sparse Representations for Control in Reinforcement Learning
Liu, Vincent
Kumaraswamy, Raksha
Le, Lei
White, Martha
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 4384 - 4391
[6] Learning Pseudometric-based Action Representations for Offline Reinforcement Learning
Gu, Pengjie
Zhao, Mengchen
Chen, Chen
Li, Dong
Hao, Jianye
An, Bo
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[7] Constructing Action Set from Basis Functions for Reinforcement Learning of Robot Control
Yamaguchi, Akihiko
Takamatsu, Jun
Ogasawara, Tsukasa
ICRA: 2009 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-7, 2009, : 4173 - 4180
[8] Lessons from reinforcement learning for biological representations of space
Muryy, Alex
Siddharth, N.
Nardelli, Nantas
Glennerster, Andrew
Torr, Philip H. S.
VISION RESEARCH, 2020, 174 : 79 - 93
[9] Hierarchical Deep Reinforcement Learning for Continuous Action Control
Yang, Zhaoyang
Merrick, Kathryn
Jin, Lianwen
Abbass, Hussein A.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (11) : 5174 - 5184
[10] Regularizing Action Policies for Smooth Control with Reinforcement Learning
Mysore, Siddharth
Mabsout, Bassel
Mancuso, Renato
Saenko, Kate
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 1810 - 1816

← 1 2 3 4 5 →