2011 IEEE International Conference on Development and Learning (ICDL)最新文献_第3页

A cognitive basis for theories of intrinsic motivation 内在动机理论的认知基础

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037327

Nisheeth Srivastava, Komal Kapoor, P. Schrater

引用次数: 3

Trying anyways: How ignoring the errors may help in learning new skills 无论如何都要尝试:忽略错误如何有助于学习新技能

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037333

B. Grzyb, J. Boedecker, M. Asada, A. P. Pobil, Linda B. Smith

引用次数: 2

Modelling early infant walking: Testing a generic CPG architecture on the NAO humanoid 早期婴儿行走建模:在NAO类人机器人上测试通用CPG架构

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037318

G. Lee, Robert J. Lowe, T. Ziemke

引用次数: 7

A neural-dynamic architecture for behavioral organization of an embodied agent 具身主体行为组织的神经动力学结构

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037353

Yulia Sandamirskaya, Mathis Richter, G. Schöner

{"title":"A neural-dynamic architecture for behavioral organization of an embodied agent","authors":"Yulia Sandamirskaya, Mathis Richter, G. Schöner","doi":"10.1109/DEVLRN.2011.6037353","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037353","url":null,"abstract":"How agents generate meaningful sequences of actions in natural environments is one of the most challenging problems in studies of natural cognition and in the design of artificial cognitive systems. Each action in a sequence must contribute to the behavioral objective, while at the same time satisfying constraints that arise from the environment, the agent's embodiment, and the agent's behavioral history. In this paper, we introduce a neural-dynamic architecture that enables selection of an appropriate action for a given task in a particular environment and is open to learning. We use the same framework of neural dynamics for all processes from perception, to representation and motor planning as well as behavioral organization. This facilitates integration and flexibility. The neural dynamic representations of particular behaviors emerge on the fly from the interplay between task and environment inputs as well as behavioral history. All behavioral states are attractors of the neural dynamics, whose instabilities lead to behavioral switches. As a result, behavioral organization is robust in the face of noisy and unreliable sensory information.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132754660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 31

Learning to react to abstractions: Accumulating adaptations in a humanoid embodiment 学习对抽象事物做出反应:在人形化身中积累适应能力

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037350

Christopher Larcombe, Anthony F. Morse, A. Cangelosi

引用次数: 1

Emergence of mirror neuron system: Immature vision leads to self-other correspondence 镜像神经元系统的出现:不成熟的视觉导致自我-他人对应

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037335

Y. Nagai, Yuji Kawai, M. Asada

{"title":"Emergence of mirror neuron system: Immature vision leads to self-other correspondence","authors":"Y. Nagai, Yuji Kawai, M. Asada","doi":"10.1109/DEVLRN.2011.6037335","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037335","url":null,"abstract":"The question of how the mirror neuron system (MNS) develops has attracted increased attention of researchers. Among various hypotheses, a widely accepted model is associative sequence learning, which acquires the MNS as a by-product of sensorimotor learning. The model, however, cannot discriminate self from others since it adopts too much simplified sensory representations. We propose a computational model for early development of the MNS, which is originated in immature vision. The model gradually increases the spatiotemporal resolution of a robot's vision while the robot learns sensorimotor mapping through primal interactions with others. In the early stage of development, the robot interprets all observed actions as equivalent due to a lower resolution, and thus associates the non-differentiated observation with motor commands. As vision develops, the robot starts discriminating actions generated by self from those by others. The initially acquired association is, however, maintained through development, which results in two types of associations: one is between motor commands and self-observation and the other between motor commands and other-observation (i.e., what the MNS does). Our experiments demonstrate that the model achieves early development of the MNS, which enables a robot to imitate others' actions.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130731334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 55

Learning geometry from sensorimotor experience 从感觉运动经验中学习几何

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037381

J. Stober, R. Miikkulainen, B. Kuipers

引用次数: 16

The two-dimensional organization of behavior 行为的二维组织

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037326

Mark B. Ring, T. Schaul, J. Schmidhuber

{"title":"The two-dimensional organization of behavior","authors":"Mark B. Ring, T. Schaul, J. Schmidhuber","doi":"10.1109/DEVLRN.2011.6037326","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037326","url":null,"abstract":"This paper addresses the problem of continual learning [1] in a new way, combining multi-modular reinforcement learning with inspiration from the motor cortex to produce a unique perspective on hierarchical behavior. Most reinforcement-learning agents represent policies monolithically using a single table or function approximator. In those cases where the policies are split among a few different modules, these modules are related to each other only in that they work together to produce the agent's overall policy. In contrast, the brain appears to organize motor behavior in a two-dimensional map, where nearby locations represent similar behaviors. This representation allows the brain to build hierarchies of motor behavior that correspond not to hierarchies of subroutines but to regions of the map such that larger regions correspond to more general behaviors. Inspired by the benefits of the brain's representation, the system presented here is a first step and the first attempt toward the two-dimensional organization of learned policies according to behavioral similarity. We demonstrate a fully autonomous multi-modular system designed for the constant accumulation of ever more sophisticated skills (the continual-learning problem). The system can split up a complex task among a large number of simple modules such that nearby modules correspond to similar policies. The eventual goal is to develop and use the resulting organization hierarchically, accessing behaviors by their location and extent in the map.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124947643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 20

An unsupervised algorithm for the induction of constructions 构造归纳法的无监督算法

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037371

Judith Gaspers, P. Cimiano, Sascha S. Griffiths, B. Wrede

引用次数: 15

Simultaneous acquisition of task and feedback models 同时获取任务和反馈模型

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037359

M. Lopes, Thomas Cederbourg, Pierre-Yves Oudeyer

引用次数: 30