116,771 Hits in 5.4 sec

AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learning [article]

Wei Fan, Kunpeng Liu, Hao Liu, Pengyang Wang, Yong Ge, Yanjie Fu
2020 arXiv   pre-print
We then develop two strategies: (1) to identify assertive and hesitant agents to diversify agent training, and (2) to enable the two trainers to take the teaching role in different stages to fuse the experiences  ...  Such a hybrid teaching strategy can help agents to learn broader knowledge, and, thereafter, be more effective.  ...  (iv) IRFS with HT (Hybrid Teaching strategy): a variant of IRFS using Hybrid Teaching strategy with two proposed trainers. TABLE I NOTATIONS.  ... 
arXiv:2008.12001v3 fatcat:hw4oehyg4vgv7mhnttz4cszz4u

SIPsmartER delivered through rural, local health districts: adoption and implementation outcomes

Kathleen J. Porter, Donna Jean Brock, Paul A. Estabrooks, Katelynn M. Perzynski, Erin R. Hecht, Pamela Ray, Natalie Kruzliakova, Eleanor S. Cantrell, Jamie M. Zoellner
2019 BMC Public Health  
However, implementation outcomes for teach-back and missed class calls and recruitment were not as strong.  ...  Delivery agents completing the two-day training, pre-lesson meetings, fidelity checklists, and post-lesson meetings at rates of 86, 75, 100, and 100%, respectively.  ...  Consent for publication Not applicable Competing interests The authors declare they have no competing interests.  ... 
doi:10.1186/s12889-019-7567-6 pmid:31533683 pmcid:PMC6751747 fatcat:vu2fat5s2rg5xjkwabml4y474a

Batch versus interactive learning by demonstration

Peng Zang, Runhe Tian, Andrea L. Thomaz, Charles L. Isbell
2010 2010 IEEE 9th International Conference on Development and Learning  
Our exploration of interactivity sheds light on how best to obtain demonstrations for LfD applications.  ...  Agents that operate in human environments will need to be able to learn new skills from everyday people. Learning from demonstration (LfD) is a popular paradigm for this.  ...  trained agent.  ... 
doi:10.1109/devlrn.2010.5578841 dblp:conf/icdl/ZangTTI10 fatcat:ldvcbimr2fa4zp6p6vui3dmmnm

FlexiTrainer: A Visual Authoring Framework for Case-Based Intelligent Tutoring Systems [chapter]

Sowmya Ramachandran, Emilio Remolina, Daniel Fu
2004 Lecture Notes in Computer Science  
FlexiTrainer provides tools for specifying the domain knowledge and derives its power from a visual behavior editor for specifying the dynamic behavior of tutoring agents that interact to deliver instruction  ...  The FlexiTrainer runtime engine is an agent based system where different instructional agents carry out teaching related actions to achieve instructional goals.  ...  Instructional agents carry out teaching-related actions to achieve instructional goals. The behaviors specified with the Behavior Editor define how agents satisfy different goals.  ... 
doi:10.1007/978-3-540-30139-4_96 fatcat:va5lknj7xzf4jlfh2c5ciengh4

On-line Dialogue Policy Learning with Companion Teaching

Lu Chen, Runzhe Yang, Cheng Chang, Zihao Ye, Xiang Zhou, Kai Yu
2017 Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers  
On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios.  ...  with more user interaction data.  ...  different teaching strategies.  ... 
doi:10.18653/v1/e17-2032 dblp:conf/eacl/ChenYCYZY17 fatcat:ju6ganm46jffbholid4l3fh5hy

A Multi-Agent approach To the Design of An Programming ICAI System

Zheng Xing Xiao
2012 Physics Procedia  
Finally interaction of multi-agent is presented , enabling the system to teaching and testing according to the student's aptitude.  ...  Programming ICAI covers the whole range of teaching and learning of programming, multi-agent approach is suitable for the development of ICAI program.  ...  Through the interaction of multi-agent, teaching strategies are implemented. 4.  ... 
doi:10.1016/j.phpro.2012.03.170 fatcat:cnwjolttvreoziabvxwd6cgrmm

Intelligent Agents in Learning Environment ABDITS

Shweta Mahlawat, O.P. Rishi, Praveen Dhyani
2015 International Journal of Computer Applications  
A crucial feature of the ABDITS personal agent is that the case based reasoning approach for student modeling.  ...  Intelligent agents are intended to examine the opportunities to enhance the teaching and to motivate the scholars to be told what they require, in an exceedingly user friendly environment that suits their  ...  agent selects appropriate education strategies for the organization of the training resources based on info urged by the user agent.  ... 
doi:10.5120/ijca2015906550 fatcat:y6a3c2l4lrdd3fccbrql4guczy

Experiments in socially guided machine learning

Andrea L. Thomaz, Guy Hoffman, Cynthia Breazeal
2006 Proceeding of the 1st ACM SIGCHI/SIGART conference on Human-robot interaction - HRI '06  
In this work we are studying the role real-time human interaction plays in training assistive robots to perform new tasks.  ...  People adjust their behavior as they develop a model of the learner, they use the reward channel for guidance as well as feedback, and they may also use it as a motivational channel.  ...  We expected that feedback would decrease over the training session, informed by related work in which Isbell et al. [1] observed habituation in an interactive teaching task.  ... 
doi:10.1145/1121241.1121315 dblp:conf/hri/ThomazHB06 fatcat:35yjrk7hvnhmbohym3diohtdm4

Reinforcement Learning in a POMDP Based Intelligent Tutoring System for Optimizing Teaching Strategies

Fangju Wang
2018 International Journal of Information and Education Technology  
The abilities to improve teaching strategies online is important for an intelligent tutoring system (ITS) to perform adaptive teaching.  ...  In our research, we have developed a reinforcement learning technique, which enables a POMDP-based ITS to learn from its teaching experience and improve teaching strategies online.  ...  Parameter Update In policy improvement, the agent learns from the system-student interactions, and continuously improves the policy for better teaching performance.  ... 
doi:10.18178/ijiet.2018.8.8.1098 fatcat:4aoa5dsq5rgldoeh3w5f47mnqa

Multiagent Culture Algorithm-Based Interactive Design of College English Online Teaching Process

Nianfan Peng, Rahim Khan
2022 Computational Intelligence and Neuroscience  
Traditional educational techniques and conceptions no longer match the need of the society for talent training.  ...  This study has the motive to examine the interactive teaching mode's application tactics in college English classrooms, particularly with the goal of improving the effectiveness of English classroom teaching  ...  Interactive Teaching Strategies Diversified Teaching Methods.  ... 
doi:10.1155/2022/3490055 pmid:35685162 pmcid:PMC9173912 fatcat:tmgbr3cmg5gjrpn7vtwq2kb63q

Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners [article]

Yun-Shiuan Chuang, Xuezhou Zhang, Yuzhe Ma, Mark K. Ho, Joseph L. Austerweil, Xiaojin Zhu
2021 arXiv   pre-print
Our results reveal how people teach using evaluative feedback and provide guidance for how engineers should design machine agents in a manner that is intuitive for people.  ...  value for its learning rate.  ...  Recent work in cognitive science and human-machine interaction has explored human teaching strategies and to what extent they are optimal.  ... 
arXiv:2009.02476v2 fatcat:uzw7vzthf5gxhl7geezwv6cntm

Curriculum Design for Teaching via Demonstrations: Theory and Applications [article]

Gaurav Yengera, Rati Devidze, Parameswaran Kamalaruban, Adish Singla
2021 arXiv   pre-print
Furthermore, we adapt our curriculum strategy to the setting where no teacher agent is present using task-specific difficulty scores.  ...  We provide a unified curriculum strategy for two popular learner models: Maximum Causal Entropy Inverse Reinforcement Learning (MaxEnt-IRL) and Cross-Entropy Behavioral Cloning (CrossEnt-BC).  ...  In particular, [17, 18] have proposed batch teaching algorithms for an IRL agent, where the teacher decides the entire set of demonstrations to provide to the learner before any interaction.  ... 
arXiv:2106.04696v3 fatcat:zdnksjefujdyzj5z6lrbqb3bk4

Reinforcement Learning with Human Teachers: Understanding How People Want to Teach Robots

Andrea L. Thomaz, Guy Hoffman, Cynthia Breazeal
2006 ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication  
While Reinforcement Learning (RL) is not traditionally designed for interactive supervisory input from a human teacher, several works in both robot and software agents have adapted it for human input by  ...  We report three main observations on how people administer feedback when teaching a robot a task through Reinforcement Learning: (a) they use the reward channel not only for feedback, but also for future-directed  ...  We present observations of the teaching strategies that the human instructors employed in training the game agent.  ... 
doi:10.1109/roman.2006.314459 dblp:conf/ro-man/ThomazHB06 fatcat:hmssozyf7rdk7ghuzzi6vaiu34

Learning to Teach [article]

Yang Fan, Fei Tian, Tao Qin, Xiang-Yang Li, Tie-Yan Liu
2018 arXiv   pre-print
In the approach, two intelligent agents interact with each other: a student model (which corresponds to the learner in traditional machine learning algorithms), and a teacher model (which determines the  ...  much less training data and fewer iterations to achieve almost the same accuracy for different kinds of DNN models (e.g., multi-layer perceptron, convolutional neural networks and recurrent neural networks  ...  ACKNOWLEDGEMENT We thank Di He for his helpful suggestions. We thank all the anonymous reviewers' comments to make the paper more comprehensive.  ... 
arXiv:1805.03643v1 fatcat:vxf6so2j4bhazmgcfqiarilxk4

A Review on Interactive Reinforcement Learning from Human Social Feedback

Jinying Lin, Zhen Ma, Randy Gomez, Keisuke Nakamura, Bo He, Guangliang Li
2020 IEEE Access  
This paper reviews methods for interactive reinforcement learning agent to learn from human social feedback and the ways of delivering feedback.  ...  Inspired by real-life biological learning scenarios, there could be many ways to provide feedback for agent learning, such as via hardware delivered, natural interaction like facial expressions, speech  ...  In addition, [11] interpreted human feedback as discrete categorical feedback strategies that depend both on the behavior the trainer is trying to teach and the trainer's teaching strategy.  ... 
doi:10.1109/access.2020.3006254 fatcat:omtnm6g6lvfenduatelslnc5ce
« Previous Showing results 1 — 15 out of 116,771 results