发布求助
文献互助 智能选刊 最新文献

2008 7th IEEE International Conference on Development and Learning最新文献

筛选
英文 中文
A reinforcement learning model of social referencing 社会参照的强化学习模型
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640844
H. Jasso, Jochen Triesch, G. Deák
{"title":"A reinforcement learning model of social referencing","authors":"H. Jasso, Jochen Triesch, G. Deák","doi":"10.1109/DEVLRN.2008.4640844","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640844","url":null,"abstract":"We present a novel computational model of social referencing. The model replicates a classic social referencing experiment where an infant is presented with a novel object and has the choice of consulting an adultpsilas informative facial expression before reacting to the object. The infant model learns the value of consulting the adultpsilas facial expression using the temporal difference learning algorithm. The model is used to make hypotheses about the reason for a lack of social referencing found in autistic individuals, based on an aversion to faces. Comparisons are made between this reinforcement learning model and a previous model based on mood contagion.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121219121","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: 8
Autism, eye-tracking, entropy 自闭症，眼球追踪，熵
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640808
Frederick Shic, K. Chawarska, Jessica Bradshaw, B. Scassellati
{"title":"Autism, eye-tracking, entropy","authors":"Frederick Shic, K. Chawarska, Jessica Bradshaw, B. Scassellati","doi":"10.1109/DEVLRN.2008.4640808","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640808","url":null,"abstract":"Using eye-tracking, we examine the scanning patterns of 2 year old and 4 year old toddlers with and without autism spectrum disorder as they view static images of faces. We use several measures, such as the entropy of scanning patterns, in order to characterize the differences in attention towards faces by these children. We find a differential pattern of both fine attention (towards specific regions of the face) as well as gross attention (looking at the faces at all) which seem to suggest different developmental trajectories for the two groups of children. We discuss the implications of these trends and the development of simple, effective, and robust measures and methodology for evaluating scanning patterns.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"2020 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128172831","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: 59
A robotic model of the development of gaze following 注视跟随发展的机器人模型
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640836
Hyundo Kim, H. Jasso, G. Deák, J. Triesch
{"title":"A robotic model of the development of gaze following","authors":"Hyundo Kim, H. Jasso, G. Deák, J. Triesch","doi":"10.1109/DEVLRN.2008.4640836","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640836","url":null,"abstract":"For humanoid robots, the skill of gaze following is a foundational component in social interaction and imitation learning.We present a robotic system capable of learning the gaze following behavior in a real-world environment. First, the system learns to detect salient objects and to distinguish a caregiverpsilas head poses in a semi-autonomous manner. Then we present multiple scenes containing different combinations of objects and head poses to the robot head. The system learns to associate the detected head pose with correct spatial location of where potentially ldquorewardingrdquo objects would be using a biologically plausible reinforcement learning mechanism.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133910743","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
Parental action modification highlighting the goal versus the means 父母行为修改强调目标与手段
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640796
Y. Nagai, K. Rohlfing
{"title":"Parental action modification highlighting the goal versus the means","authors":"Y. Nagai, K. Rohlfing","doi":"10.1109/DEVLRN.2008.4640796","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640796","url":null,"abstract":"Parents significantly alter their infant-directed actions compared to adult-directed ones, which is assumed to assist the infantspsila processing of the actions. This paper discusses differences in parental action modification depending on whether the goal or the means is more crucial. When demonstrating a task to an infant, parents try to emphasize the important aspects of the task by suppressing or adding their movement. Our hypothesis is that in a goal-crucial task, the initial and final states of the task should be highlighted by parental actions, whereas in a means-crucial task the movement is underlined. Our analysis using a saliency-based attention model partially verified it: When focusing on the goal, parents tended to emphasize the initial and final states of the objects used in the task by taking a long pause before/after they started/fulfilled the task. When focusing on the means, parents shook the object to highlight it, which consequently made its state invisible. We discuss our findings regarding the uniqueness and commonality of the parental action modification. We also describe our contribution to the development of robots capable of imitating human actions.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130939443","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: 13
TAMER: Training an Agent Manually via Evaluative Reinforcement TAMER:通过评估强化手动训练Agent
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640845
W. B. Knox, P. Stone
{"title":"TAMER: Training an Agent Manually via Evaluative Reinforcement","authors":"W. B. Knox, P. Stone","doi":"10.1109/DEVLRN.2008.4640845","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640845","url":null,"abstract":"Though computers have surpassed humans at many tasks, especially computationally intensive ones, there are many tasks for which human expertise remains necessary and/or useful. For such tasks, it is desirable for a human to be able to transmit knowledge to a learning agent as quickly and effortlessly as possible, and, ideally, without any knowledge of the details of the agentpsilas learning process. This paper proposes a general framework called Training an Agent Manually via Evaluative Reinforcement (TAMER) that allows a human to train a learning agent to perform a common class of complex tasks simply by giving scalar reward signals in response to the agentpsilas observed actions. Specifically, in sequential decision making tasks, an agent models the humanpsilas reward function and chooses actions that it predicts will receive the most reward. Our novel algorithm is fully implemented and tested on the game Tetris. Leveraging the human trainerspsila feedback, the agent learns to clear an average of more than 50 lines by its third game, an order of magnitude faster than the best autonomous learning agents.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127521031","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: 136
Trait or situation? ∼ Cultural differences in judgments of emotion ∼ 特质还是情境?情感判断的文化差异
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640823
M. Kuwabara, Ji Yeon Son, L.B. Smith
{"title":"Trait or situation? ∼ Cultural differences in judgments of emotion ∼","authors":"M. Kuwabara, Ji Yeon Son, L.B. Smith","doi":"10.1109/DEVLRN.2008.4640823","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640823","url":null,"abstract":"Traditional research in cognition assumes that fundamental processes such as memory and attention are universal. However, a growing number of studies suggest cultural differences in the attention and evaluation of information (Masuda & Nisbet 2001; Maass, et al 2006; Markus & Kitayama 1991; Heddenn, et al 2008). One cultural comparison, between Westerners, such as Americans and Easterners such as Japanese suggest that whereas Westerners typically focus on a central single object in a scene Easterners often integrate their judgment of the focal object with surrounding contextual cues. The research reported here considers this cultural difference in the context of childrenpsilas developing understanding of emotions. The results demonstrate cultural differences in children as young as 3 and 4 years of age. In particular, Japanese children judge emotions based more on contextual information than facial expressions whereas the opposite is true for American children. The addition of language (labeling the emotions) increases the cultural differences.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124511283","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: 4
What does shaping mean for computational reinforcement learning? 塑形对于计算强化学习意味着什么?
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640832
Tom Erez, W. Smart
{"title":"What does shaping mean for computational reinforcement learning?","authors":"Tom Erez, W. Smart","doi":"10.1109/DEVLRN.2008.4640832","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640832","url":null,"abstract":"This paper considers the role of shaping in applications of reinforcement learning, and proposes a formulation of shaping as a homotopy-continuation method. By considering reinforcement learning tasks as elements in an abstracted task space, we conceptualize shaping as a trajectory in task space, leading from simple tasks to harder ones. The solution of earlier, simpler tasks serves to initialize and facilitate the solution of later, harder tasks. We list the different ways reinforcement learning tasks may be modified, and review cases where continuation methods were employed (most of which were originally presented outside the context of shaping). We contrast our proposed view with previous work on computational shaping, and argue against the often-held view that equates shaping with a rich reward scheme. We conclude by discussing a proposed research agenda for the computational study of shaping in the context of reinforcement learning.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126983418","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: 48
Dynamic systems modeling of pre-schoolers’ response to an emotionally stressful event 学龄前儿童对情绪压力事件反应的动态系统建模
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640828
M. Plunkett, J. Szemraj, D. Tilbury, T. Tardif, B. Felt, N. Kaciroti, R. Angulo-Barroso, T. Shafir, L. Wang
{"title":"Dynamic systems modeling of pre-schoolers’ response to an emotionally stressful event","authors":"M. Plunkett, J. Szemraj, D. Tilbury, T. Tardif, B. Felt, N. Kaciroti, R. Angulo-Barroso, T. Shafir, L. Wang","doi":"10.1109/DEVLRN.2008.4640828","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640828","url":null,"abstract":"This paper presents preliminary results for using dynamic systems models to describe physiological and behavioral responses (cortisol and activity) to emotionally stressful events. Linear discrete-time models are used to approximate the nonlinear model of the LHPA axis around an assumed nominal operating condition. Measurements are taken of cortisol (from saliva) and activity (with an accelerometer). These two measurements are considered as either inputs or outputs of the model. Modeling choices are discussed in detail. Results are presented that indicate activity is better interpreted as an input and cortisol as an output. In addition, the paper discusses briefly how the resulting dynamic systems models can be used for statistical analysis, as well as for integrating across multiple levels of stress responses.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115001139","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: 0
Hierarchical voting experts: An unsupervised algorithm for hierarchical sequence segmentation 分层投票专家:一种分层序列分割的无监督算法
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640827
Matthew Miller, A. Stoytchev
{"title":"Hierarchical voting experts: An unsupervised algorithm for hierarchical sequence segmentation","authors":"Matthew Miller, A. Stoytchev","doi":"10.1109/DEVLRN.2008.4640827","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640827","url":null,"abstract":"This paper extends the voting experts (VE) algorithm for unsupervised segmentation of sequences to create the hierarchical voting experts (HVE) algorithm for unsupervised segmentation of hierarchically structured sequences. The paper evaluates the strengths and weaknesses of the HVE algorithm to identify its proper domain of application. The paper also shows how higher order models of the sequence data can be used to improve lower level segmentation accuracy.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130155303","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: 16
Motor initiated expectation through top-down connections as abstract context in a physical world 在物理世界中，运动通过自上而下的连接作为抽象情境而启动期望
2008 7th IEEE International Conference on Development and Learning Pub Date : 2008-10-10 DOI: 10.1109/DEVLRN.2008.4640815
M. Luciw, J. Weng, Shuqing Zeng
{"title":"Motor initiated expectation through top-down connections as abstract context in a physical world","authors":"M. Luciw, J. Weng, Shuqing Zeng","doi":"10.1109/DEVLRN.2008.4640815","DOIUrl":"https://doi.org/10.1109/DEVLRN.2008.4640815","url":null,"abstract":"Recently, it has been shown that top-down connections improve recognition in supervised learning. In the work presented here, we show how top-down connections represent temporal context as expectation and how such expectation assists perception in a continuously changing physical world, with which an agent interacts during its developmental learning. In experiments in object recognition and vehicle recognition using two types of networks (which derive either global or local features), it is shown how expectation greatly improves performance, to nearly 100% after the transition periods. We also analyze why expectation will improve performance in such real world contexts.","PeriodicalId":366099,"journal":{"name":"2008 7th IEEE International Conference on Development and Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131073632","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: 19
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信