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

[41] Hierarchical reinforcement learning for kinematic control tasks with parameterized action spaces
Jingyu Cao
Lu Dong
Changyin Sun
Neural Computing and Applications, 2024, 36 : 323 - 336
[42] Model-based hierarchical reinforcement learning and human action control
Botvinick, Matthew
Weinstein, Ari
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES, 2014, 369 (1655)
[43] Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control
Cheng, Hai
Bertizzolo, Lorenzo
D'oro, Salvatore
Buczek, John
Melodia, Tommaso
Bentley, Elizabeth Serena
IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY, 2021, 2 : 1486 - 1504
[44] Forest Fire Control with Learning from Demonstration and Reinforcement Learning
Hammond, Travis
Schaap, Dirk Jelle
Sabatelli, Matthia
Wiering, Marco A.
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[45] A Comparison of Different State Representations for Reinforcement Learning Based Variable Speed Limit Control
Kusic, Kresimir
Ivanjko, Edouard
Greguric, Martin
2018 26TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED), 2018, : 266 - 271
[46] Dual representations for dynamic programming and reinforcement learning
Wang, Tao
Bowling, Michael
Schuurmans, Dale
2007 IEEE INTERNATIONAL SYMPOSIUM ON APPROXIMATE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2007, : 44 - +
[47] CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Laskin, Michael
Srinivas, Aravind
Abbeel, Pieter
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
[48] A Geometric Perspective on Optimal Representations for Reinforcement Learning
Bellemare, Marc G.
Dabney, Will
Dadashi, Robert
Taiga, Adrien Ali
Castro, Pablo Samuel
Le Roux, Nicolas
Schuurmans, Dale
Lattimore, Tor
Lyle, Clare
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[49] Developing PFC representations using reinforcement learning
Reynolds, Jeremy R.
O'Reilly, Randall C.
COGNITION, 2009, 113 (03) : 281 - 292
[50] Combined Reinforcement Learning via Abstract Representations
Francois-Lavet, Vincent
Bengio, Yoshua
Precup, Doina
Pineau, Joelle
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, : 3582 - 3589

← 1 2 3 4 5 →