2011 IEEE International Conference on Development and Learning (ICDL)最新文献

Learning regions for building a world model from clusters in probability distributions 从概率分布中的聚类构建世界模型的学习区域

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037339

W. Slowinski, Frank Guerin

{"title":"Learning regions for building a world model from clusters in probability distributions","authors":"W. Slowinski, Frank Guerin","doi":"10.1109/DEVLRN.2011.6037339","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037339","url":null,"abstract":"A developing agent learns a model of the world by observing regularities occurring in its sensory inputs. In a continuous domain where the model is represented by a set of rules, a significant part of the task of learning such a model is to find appropriate intervals within the continuous state variables, such that these intervals can be used to define rules whose predictions are reliable. We propose a technique to find such intervals (or regions) by means of finding clusters on approximate probability distributions of sensory variables. We compare this cluster-based method with an alternative landmark-based algorithm. We evaluate both techniques on a data log recorded in a simulation based on OpenArena, a three-dimensional first-person-perspective computer game, and demonstrate the results of how the techniques can learn rules which describe walking behaviour. While both techniques work reasonably well, the clustering approach seems to give more “natural” regions which correspond more closely to what a human would expect; we speculate that such regions should be more useful if they are to form a basis for further learning of higher order rules.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"11 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":"121060106","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: 2

Early-stage vision of composite scenes for spatial learning and navigation 空间学习和导航合成场景的早期视觉

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037348

Olivier L. Georgeon, James B. Marshall, Pierre-Yves Ronot

引用次数: 5

Teaching and executing verb phrases 教授和执行动词短语

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037340

D. Hewlett, Thomas J. Walsh, P. Cohen

引用次数: 7

Contingency allows the robot to spot the tutor and to learn from interaction 偶然性允许机器人识别导师，并从互动中学习

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037341

K. Lohan, K. Pitsch, K. Rohlfing, K. Fischer, J. Saunders, H. Lehmann, Chrystopher L. Nehaniv, B. Wrede

{"title":"Contingency allows the robot to spot the tutor and to learn from interaction","authors":"K. Lohan, K. Pitsch, K. Rohlfing, K. Fischer, J. Saunders, H. Lehmann, Chrystopher L. Nehaniv, B. Wrede","doi":"10.1109/DEVLRN.2011.6037341","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037341","url":null,"abstract":"Aiming at artificial system learning from a human tutor elicit tutoring behavior, which we implemented on the robotic platform iCub. For the evaluation of the system with users, we considered a contingency module that is developed to elicit tutoring behavior, which we then evaluate by implementing this module on the robotic platform iCub and within an interaction with the users. For the evaluation of our system, we consider not only the participant's behavior but also the system's log-files as dependent variables (as it was suggested in [15] for the improvement of HRI design). We further applied Sequential Analysis as a qualitative method that provides micro-analytical insights into the sequential structure of the interaction. This way, we are able to investigate a closer interrelationship between robot's and tutor's actions and how they respond to each other. We focus on two cases: In the first case, the system module was reacting to the interaction partner appropriately; in the second case, the contingency module failed to spot the tutor. We found that the contingency module enables the robot to engage in an interaction with the human tutor who orients to the robot's conduct as appropriate and responsive. In contrast, when the robot did not engage in an appropriate responsive interaction, the tutor oriented more towards the object while gazing less at the robot.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"37 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":"128222440","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: 23

Modelling the face-to-face effect: Sensory population dynamics and active vision can contribute to perception of social context 模拟面对面效应:感官群体动态和主动视觉可以促进对社会环境的感知

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037366

N. Wilkinson, G. Metta, G. Gredebäck

引用次数: 10

Hierarchical reinforcement learning and central pattern generators for modeling the development of rhythmic manipulation skills 层次强化学习和中心模式生成器，用于模拟节奏操纵技能的发展

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037370

A. Ciancio, L. Zollo, E. Guglielmelli, Daniele Caligiore, G. Baldassarre

{"title":"Hierarchical reinforcement learning and central pattern generators for modeling the development of rhythmic manipulation skills","authors":"A. Ciancio, L. Zollo, E. Guglielmelli, Daniele Caligiore, G. Baldassarre","doi":"10.1109/DEVLRN.2011.6037370","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037370","url":null,"abstract":"The development of manipulation skills is a fundamental process for young primates as it leads them to acquire the capacity to modify the world to their advantage. As other motor skills, manipulation develops on the basis of motor babbling processes which are initially heavily based on the production of rhythmic movements. We propose a computational bio-inspired model to investigate the development of functional rhythmic hand skills from initially unstructured movements. The model is based on a hierarchical reinforcement-learning actor-critic model that searches the parameters of a set of central pattern generators (CPGs) having different degrees of sophistication. The model is tested with a simulated robotic hand engaged in rotating bottle cap-like objects having different shape and size. The results show that the model is capable of developing skills based on different combinations of CPGs so as to suitably manipulate the different objects. Overall, the model shows to be a valuable tool for the study of the development of rhythmic manipulation skills in primates.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"34 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":"127882104","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: 14

Measuring word learning performance in computational models and infants 测量计算模型和婴儿的单词学习表现

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037354

C. Bergmann, L. Boves, L. T. Bosch

引用次数: 2

Reward-driven learning of sensorimotor laws and visual features 感觉运动规律和视觉特征的奖励驱动学习

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037358

Jens Kleesiek, A. Engel, C. Weber, S. Wermter

引用次数: 2

Joint development of disparity tuning and vergence control 视差调节与收敛控制的联合开发

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037338

Wanting Sun, Bertram E. Shi

{"title":"Joint development of disparity tuning and vergence control","authors":"Wanting Sun, Bertram E. Shi","doi":"10.1109/DEVLRN.2011.6037338","DOIUrl":"https://doi.org/10.1109/DEVLRN.2011.6037338","url":null,"abstract":"Behavior and sensory perception are mutually dependent. Sensory perception drives behavior, but behavior can also influence the development of sensory perception, by altering the statistics of the sensory input. Thus, there is a “chicken-and-egg” problem as to which arises first. We propose here a solution to this problem in the context of the neural processing of binocular disparity and the behavioral control of binocular vergence to maintain fixation. We show that it is possible for both the neural processing and the control policy to develop simultaneously. In particular, we assume that the neural processing develops through learning a sparse complex-cell representation of the input, and that the control policy simultaneously develops through reinforcement learning to maximize the activity in this complex cell representation. These processes are coupled. The control policy determines the statistics of the input, which determines the sparse coding that develops, which in turn determines the reward maximized by the control policy. Our experiments show that both disparity selective binocular receptive fields and a successful binocular fixation policy develop. Our results underline the importance of behavior, as we show that on the same input but in the absence of learned behavior, much fewer disparity selective binocular receptive fields develop.","PeriodicalId":256921,"journal":{"name":"2011 IEEE International Conference on Development and Learning (ICDL)","volume":"13 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":"115526984","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: 9

Bootstrapping intrinsically motivated learning with human demonstration 用人类示范引导内在动机学习

2011 IEEE International Conference on Development and Learning (ICDL) Pub Date : 2011-10-10 DOI: 10.1109/DEVLRN.2011.6037329

S. Nguyen, Adrien Baranes, Pierre-Yves Oudeyer

引用次数: 26