scholarly journals Refining HTN Methods via Task Insertion with Preferences

2020 ◽  
Vol 34 (06) ◽  
pp. 10009-10016
Author(s):  
Zhanhao Xiao ◽  
Hai Wan ◽  
Hankui Hankz Zhuo ◽  
Andreas Herzig ◽  
Laurent Perrussel ◽  
...  
Keyword(s):  
Real World ◽  
Domain Knowledge ◽  
The Other ◽  
Learning Approaches ◽  
Minimal Set ◽  
Domain Experts ◽  
Hierarchical Task Network ◽  
Learning Framework ◽  
Htn Planning ◽  
Method Substitution

Hierarchical Task Network (HTN) planning is showing its power in real-world planning. Although domain experts have partial hierarchical domain knowledge, it is time-consuming to specify all HTN methods, leaving them incomplete. On the other hand, traditional HTN learning approaches focus only on declarative goals, omitting the hierarchical domain knowledge. In this paper, we propose a novel learning framework to refine HTN methods via task insertion with completely preserving the original methods. As it is difficult to identify incomplete methods without designating declarative goals for compound tasks, we introduce the notion of prioritized preference to capture the incompleteness possibility of methods. Specifically, the framework first computes the preferred completion profile w.r.t. the prioritized preference to refine the incomplete methods. Then it finds the minimal set of refined methods via a method substitution operation. Experimental analysis demonstrates that our approach is effective, especially in solving new HTN planning instances.

scholarly journals HTN Learning via Transfer Learning of Domain Landmarks

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Greg Pennisi ◽  
Morgan Fine-Morris ◽  
Michael W. Floyd ◽  
Bryan Auslander ◽  
Hector Munoz-Avila ◽  
...  
Keyword(s):  
Domain Knowledge ◽  
Knowledge Engineering ◽  
Hierarchical Task Network ◽  
Htn Planning ◽  
Engineering Requirement ◽  
Planning Methods ◽  
Important Landmark ◽  
Novel Method ◽  
Amount Of Knowledge ◽  
Problem Solvers

Hierarchical Task Network (HTN) planning uses task-subtask relationships to break complex problems into more manageable subtasks, similar to how human problem-solvers plan. However, one limitation of HTN planning is that it requires domain knowledge in the form of planning methods to perform this task decomposition. Recent work has partially alleviated this knowledge engineering requirement by learning HTN methods from traces of observed behavior. Although this greatly reduces the amount of knowledge that must be encoded by a domain expert, it requires a large collection of traces in order to infer important landmark states that are used during trace segmentation and method learning. In this paper we present a novel method for landmark inference that transfers knowledge of landmarks from previously encountered environments to new environments without requiring any traces from the new environment. We evaluate our work in a logistics planning domain and show that our approach performs comparably to the existing landmark inference method but requires far fewer traces.

scholarly journals Unified learning to enhance adaptive behavior of simulation objects

SIMULATION ◽  
2018 ◽  
Vol 94 (11) ◽  
pp. 979-992
Author(s):  
Hyo-Cheol Lee ◽  
Seok-Won Lee
Keyword(s):  
Real World ◽  
Military Training ◽  
The Other ◽  
Data Driven ◽  
Learning Approach ◽  
Simulation Environment ◽  
New Approach ◽  
Domain Experts ◽  
Training Simulation ◽  
Game Simulation

Modeling and simulation are methods of validating new systems that are risky to be directly deployed in the real world. During the simulation, the simulation environment continuously changes and simulation objects correspondingly behave according to the changing situations. In general, modeling the behavior for all possible situations is extremely difficult when the rationale is unknown. Therefore, in order to adapt to the changing situation, it is important to recognize the rationale behind the behaviors of the simulation object. However, in many cases, even though the rationale is unknown or difficult to recognize, the simulation requires reasonable behaviors such as a commander’s decision in a war game simulation and a driver’s behavior in rush hours. In this study, we propose a new approach to determine the behavior of simulation objects under changing situations. The proposal is a unified learning approach that integrates two methods, data-driven and knowledge-driven approaches, which allow simulation objects to learn behavioral knowledge from experience as well as from domain experts performing the simulation and reuse verified knowledge. By combining both approaches, we supplement the shortcomings of one method with the strengths of the other. To verify our method, we apply the proposed approach to a military training simulation.

Fostering Collaborative Autonomy: The Roles of Cooperative and Collaborative Learning

Relay Journal ◽  
2018 ◽  
pp. 360-381
Author(s):  
Gordon Myskow ◽  
Phillip A. Bennett ◽  
Hisako Yoshimura ◽  
Kyoko Gruendel ◽  
Takuto Marutani ◽  
...  
Keyword(s):  
Collaborative Learning ◽  
Cooperative Learning ◽  
Learner Autonomy ◽  
The Other ◽  
Learning Activities ◽  
Educational Context ◽  
Learning Approaches ◽  
Group Interactions ◽  
Collaborative Autonomy ◽  
Over Time

The distinction between Cooperative and Collaborative Learning approaches is not a clear one. Some use the terms interchangeably while others consider Cooperative Learning to be a type of Collaborative Learning. Still others clearly differentiate between them, characterizing Cooperative Learning as more highly structured in its procedures, involving a great deal of intervention by the teacher to plan and orchestrate group interactions. Collaborative Learning, on the other hand, presupposes some degree of learner autonomy－that groups can work effectively toward shared goals and monitor their own progress. This paper takes the view that the distinction between Cooperative and Collaborative Learning is a useful one and that both approaches can play valuable roles in fostering autonomous interaction. It argues that while Collaborative Learning formations may be the ultimate goal for teachers wishing to develop learner autonomy, Cooperative Learning is a valuable means for modeling the skills and abilities to help students get there. The discussion begins with an overview of the two approaches, focusing on their implementation in the Japanese educational context. It then presents seven highly structured Cooperative Learning activities and shows how they can be modified and extended over time to encourage more autonomous interaction.

Improving the External Validity of Conjoint Analysis: The Essential Role of Profile Distribution

2021 ◽  
pp. 1-27 ◽  
Author(s):  
Brandon de la Cuesta ◽  
Naoki Egami ◽  
Kosuke Imai
Keyword(s):  
Conjoint Analysis ◽  
Real World ◽  
External Validity ◽  
Causal Effect ◽  
The Other ◽  
Estimation Methods ◽  
Social Scientists ◽  
Actual Distribution ◽  
Open Source Software Package ◽  
Profile Distribution

Abstract Conjoint analysis has become popular among social scientists for measuring multidimensional preferences. When analyzing such experiments, researchers often focus on the average marginal component effect (AMCE), which represents the causal effect of a single profile attribute while averaging over the remaining attributes. What has been overlooked, however, is the fact that the AMCE critically relies upon the distribution of the other attributes used for the averaging. Although most experiments employ the uniform distribution, which equally weights each profile, both the actual distribution of profiles in the real world and the distribution of theoretical interest are often far from uniform. This mismatch can severely compromise the external validity of conjoint analysis. We empirically demonstrate that estimates of the AMCE can be substantially different when averaging over the target profile distribution instead of uniform. We propose new experimental designs and estimation methods that incorporate substantive knowledge about the profile distribution. We illustrate our methodology through two empirical applications, one using a real-world distribution and the other based on a counterfactual distribution motivated by a theoretical consideration. The proposed methodology is implemented through an open-source software package.

Regulations and Norms for Reuse of Residual Clinical Biospecimens and Health Data

2021 ◽  
pp. 019394592110292
Author(s):  
Elizabeth E. Umberfield ◽  
Sharon L. R. Kardia ◽  
Yun Jiang ◽  
Andrea K. Thomer ◽  
Marcelline R. Harris
Keyword(s):  
Informed Consent ◽  
Scoping Review ◽  
Real World ◽  
Genetic Information ◽  
Final Analysis ◽  
Health Data ◽  
Federal Regulations ◽  
Secondary Research ◽  
Domain Experts ◽  
Key Issues

Nurse scientists are increasingly interested in conducting secondary research using real world collections of biospecimens and health data. The purposes of this scoping review are to (a) identify federal regulations and norms that bear authority or give guidance over reuse of residual clinical biospecimens and health data, (b) summarize domain experts’ interpretations of permissions of such reuse, and (c) summarize key issues for interpreting regulations and norms. Final analysis included 25 manuscripts and 23 regulations and norms. This review illustrates contextual complexity for reusing residual clinical biospecimens and health data, and explores issues such as privacy, confidentiality, and deriving genetic information from biospecimens. Inconsistencies make it difficult to interpret, which regulations or norms apply, or if applicable regulations or norms are congruent. Tools are necessary to support consistent, expert-informed consent processes and downstream reuse of residual clinical biospecimens and health data by nurse scientists.

scholarly journals Goal-driven active learning

2021 ◽  
Vol 35 (2) ◽  
Author(s):  
Nicolas Bougie ◽  
Ryutaro Ichise
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Learning Process ◽  
Real World ◽  
Imitation Learning ◽  
Learning Approaches ◽  
Wide Range ◽  
Fixed Set ◽  
Complex Decision Making ◽  
Complex Decision

AbstractDeep reinforcement learning methods have achieved significant successes in complex decision-making problems. In fact, they traditionally rely on well-designed extrinsic rewards, which limits their applicability to many real-world tasks where rewards are naturally sparse. While cloning behaviors provided by an expert is a promising approach to the exploration problem, learning from a fixed set of demonstrations may be impracticable due to lack of state coverage or distribution mismatch—when the learner’s goal deviates from the demonstrated behaviors. Besides, we are interested in learning how to reach a wide range of goals from the same set of demonstrations. In this work we propose a novel goal-conditioned method that leverages very small sets of goal-driven demonstrations to massively accelerate the learning process. Crucially, we introduce the concept of active goal-driven demonstrations to query the demonstrator only in hard-to-learn and uncertain regions of the state space. We further present a strategy for prioritizing sampling of goals where the disagreement between the expert and the policy is maximized. We evaluate our method on a variety of benchmark environments from the Mujoco domain. Experimental results show that our method outperforms prior imitation learning approaches in most of the tasks in terms of exploration efficiency and average scores.

scholarly journals A Review of Recent Deep Learning Approaches in Human-Centered Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2514
Author(s):  
Tharindu Kaluarachchi ◽  
Andrew Reis ◽  
Suranga Nanayakkara
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Review Paper ◽  
Learning Systems ◽  
Learning Approaches ◽  
Application Development ◽  
Research Gaps ◽  
Domain Experts ◽  
Working Definition ◽  
Real World Application

After Deep Learning (DL) regained popularity recently, the Artificial Intelligence (AI) or Machine Learning (ML) field is undergoing rapid growth concerning research and real-world application development. Deep Learning has generated complexities in algorithms, and researchers and users have raised concerns regarding the usability and adoptability of Deep Learning systems. These concerns, coupled with the increasing human-AI interactions, have created the emerging field that is Human-Centered Machine Learning (HCML). We present this review paper as an overview and analysis of existing work in HCML related to DL. Firstly, we collaborated with field domain experts to develop a working definition for HCML. Secondly, through a systematic literature review, we analyze and classify 162 publications that fall within HCML. Our classification is based on aspects including contribution type, application area, and focused human categories. Finally, we analyze the topology of the HCML landscape by identifying research gaps, highlighting conflicting interpretations, addressing current challenges, and presenting future HCML research opportunities.

scholarly journals Analysis of the Nosema Cells Identification for Microscopic Images

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3068
Author(s):  
Soumaya Dghim ◽  
Carlos M. Travieso-González ◽  
Radim Burget
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
The Other ◽  
Support Vector ◽  
Learning Approaches ◽  
Microscopic Images ◽  
Trained Neural Network ◽  
Nosema Disease

The use of image processing tools, machine learning, and deep learning approaches has become very useful and robust in recent years. This paper introduces the detection of the Nosema disease, which is considered to be one of the most economically significant diseases today. This work shows a solution for recognizing and identifying Nosema cells between the other existing objects in the microscopic image. Two main strategies are examined. The first strategy uses image processing tools to extract the most valuable information and features from the dataset of microscopic images. Then, machine learning methods are applied, such as a neural network (ANN) and support vector machine (SVM) for detecting and classifying the Nosema disease cells. The second strategy explores deep learning and transfers learning. Several approaches were examined, including a convolutional neural network (CNN) classifier and several methods of transfer learning (AlexNet, VGG-16 and VGG-19), which were fine-tuned and applied to the object sub-images in order to identify the Nosema images from the other object images. The best accuracy was reached by the VGG-16 pre-trained neural network with 96.25%.

scholarly journals Reinforcement Learning Approaches in Social Robotics

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1292
Author(s):  
Neziha Akalin ◽  
Amy Loutfi
Keyword(s):  
Reinforcement Learning ◽  
Real World ◽  
Social Robotics ◽  
Research Field ◽  
Social Robots ◽  
Learning Approaches ◽  
Reward Function ◽  
Optimal Behavior ◽  
Learning Challenges ◽  
Starting Point

This article surveys reinforcement learning approaches in social robotics. Reinforcement learning is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both reinforcement learning and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. We present a thorough analysis of reinforcement learning approaches in social robotics. In addition to a survey, we categorize existent reinforcement learning approaches based on the used method and the design of the reward mechanisms. Moreover, since communication capability is a prominent feature of social robots, we discuss and group the papers based on the communication medium used for reward formulation. Considering the importance of designing the reward function, we also provide a categorization of the papers based on the nature of the reward. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view of real-world reinforcement learning challenges and proposed solutions, the points that remain to be explored, including the approaches that have thus far received less attention is also given in the paper. Thus, this paper aims to become a starting point for researchers interested in using and applying reinforcement learning methods in this particular research field.

Sign in / Sign up

Export Citation Format

Share Document