
Artificial Intelligence in Education
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This two-volume set LNCS 11625 and 11626 constitutes the refereed proceedings of the 20th International Conference on Artificial Intelligence in Education, AIED 2019, held in Chicago, IL, USA, in June 2019.
The 45 full papers presented together with 41 short, 10 doctoral consortium, 6 industry, and 10 workshop papers were carefully reviewed and selected from 177 submissions. AIED 2019 solicits empirical and theoretical papers particularly in the following lines of research and application: Intelligent and interactive technologies in an educational context; Modelling and representation; Models of teaching and learning; Learning contexts and informal learning; Evaluation; Innovative applications; Intelligent techniques to support disadvantaged schools and students, inequity and inequality in education.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Abstracts of Keynotes
- Learning to Learn Differently
- Human Development and Augmented Intelligence
- Duolingo: Free Language Education for the World
- Contents - Part I
- Contents - Part II
- Towards the Identification of Propaedeutic Relations in Textbooks
- 1 Introduction
- 2 Background and Related Work
- 3 Proposed Method
- 4 Experimental Evaluation
- 4.1 Results and Discussion
- 5 Conclusion and Limits
- References
- Investigating Help-Giving Behavior in a Cross-Platform Learning Environment
- 1 Introduction
- 2 System Description
- 3 Method
- 3.1 Participants
- 3.2 Procedure
- 3.3 Measures
- 4 Results
- 5 Discussion and Conclusion
- References
- Predicting Academic Performance: A Bootstrapping Approach for Learning Dynamic Bayesian Networks
- 1 Introduction
- 2 Related Work
- 3 Method
- 3.1 Datasets
- 3.2 Resampling with Bootstrapping
- 3.3 Bayesian Structure Learning
- 3.4 Bayesian Parameter Learning
- 4 Experimental Results
- 5 Confidence Interval Results
- 6 Conclusion and Future Work
- References
- The Impact of Student Model Updates on Contingent Scaffolding in a Natural-Language Tutoring System
- Abstract
- 1 Introduction
- 2 Rimac: An Adaptive Natural-Language Tutoring System
- 3 Testing the System
- 3.1 Conditions
- 3.2 Participants
- 3.3 Materials
- 3.4 Protocol
- 3.5 Results
- 4 Discussion and Future Work
- Acknowledgments
- References
- Item Ordering Biases in Educational Data
- 1 Introduction
- 2 Background
- 2.1 Used Data
- 2.2 Simulations
- 3 Item Ordering Bias
- 4 Understanding Data
- 5 Algorithms for Dynamic Item Ordering
- 5.1 Algorithms
- 5.2 Experiments
- 6 Discussion
- References
- A Comparative Study on Question-Worthy Sentence Selection Strategies for Educational Question Generation
- 1 Introduction
- 2 Methodology
- 2.1 Sentence Selection Strategies
- 2.2 Evaluation Method
- 3 Experiments
- 3.1 Experimental Setup
- 3.2 Results and Analysis
- 4 Conclusion and Future Work
- References
- Effect of Discrete and Continuous Parameter Variation on Difficulty in Automatic Item Generation
- 1 Introduction
- 2 Experimental Data
- 2.1 PrairieLearn and the Computer-Based Testing Facility
- 2.2 Detailed Data Specification
- 3 Discrete Parameters
- 3.1 Analysis Method for Discrete Parameters
- 3.2 Results for Discrete Parameters
- 3.3 Manual Analysis of Outliers for Discrete Parameters
- 4 Continuous Parameters
- 4.1 Analysis Method for Continuous Parameters
- 4.2 Results for Continuous Parameters
- 4.3 Manual Analysis of Outliers for Continuous Parameters
- 5 Limitations
- 6 Conclusion
- References
- Automated Summarization Evaluation (ASE) Using Natural Language Processing Tools
- Abstract
- 1 Introduction
- 1.1 Summarization
- 1.2 Automated Summarization Evaluation (ASE)
- 1.3 Current Study
- 2 Method
- 2.1 Data
- 2.2 Summary Rating
- 2.3 Linguistic Features
- 2.4 Statistical Analysis
- 3 Results
- 4 Discussion
- 5 Conclusion
- Acknowledgments
- References
- The Importance of Automated Real-Time Performance Feedback in Virtual Reality Temporal Bone Surgery Training
- 1 Introduction
- 2 Background
- 3 Methodology
- 4 Results
- 5 Discussion
- 6 Conclusion
- References
- Autonomy and Types of Informational Text Presentations in Game-Based Learning Environments
- Abstract
- 1 Introduction
- 1.1 Autonomy in Game-Based Learning Environments
- 1.2 Application of the Cognitive Theory of Multimedia Learning to GBLEs
- 1.3 Eye Tracking in GBLEs
- 1.4 Crystal Island Environment
- 2 Current Study
- 3 Method
- 3.1 Participants
- 3.2 Experimental Conditions
- 3.3 Materials
- 3.4 Experimental Procedure
- 3.5 Coding and Scoring
- 4 Results
- 4.1 Research Question 1: Do PLGs Differ Between the Full and Partial Agency Conditions?
- 4.2 Research Question 2: Do Fixation Durations on Different Types Of Informational Text Presentations in the Environment Predict PLG?
- 4.3 Research Question 3: Do Fixation Durations on Different Types of Informational Text Presentations Differ Between the Full and Partial Agency Conditions?
- 5 Discussion
- 5.1 Future Directions: More AI in GBLEs?
- Acknowledgements
- References
- Examining Gaze Behaviors and Metacognitive Judgments of Informational Text Within Game-Based Learning Environments
- Abstract
- 1 Introduction
- 1.1 Self-regulated Learning and Metacognitive Monitoring
- 1.2 Metacognitive Judgments in Game-Based Learning Environments
- 1.3 Eye Tracking in Game-Based Learning Environments
- 1.4 Crystal Island: A Game-Based Learning Environment
- 1.5 Related Works
- 2 Current Study, Research Questions, and Hypotheses
- 3 Method
- 3.1 Participants
- 3.2 Crystal Island Conditions
- 3.3 Materials
- 3.4 Experimental Procedure
- 3.5 Coding and Scoring
- 4 Results
- 5 Discussion
- 5.1 Implications for Adaptive Game-Based Learning Environments
- Acknowledgements
- References
- Using "Idealized Peers" for Automated Evaluation of Student Understanding in an Introductory Psychology Course
- Abstract
- 1 Introduction
- 1.1 Generative Activities
- 1.2 Using Latent Semantic Analysis in Automated Evaluation of Responses
- 2 Corpus and Human Scoring of Responses
- 2.1 Corpus
- 2.2 Human Scoring of Responses
- 2.3 Idealized-Peer Response
- 3 Results Using Automated Scoring Indices
- 3.1 Automated Scoring Indices
- 3.2 Relation of Automated Scoring to Human Scoring
- 3.3 Relation of Automated Scoring to Student Understanding
- 3.4 Unique Contribution of LSAIDEAL Over and Above Reader Characteristics
- 3.5 Comparison of LSAIDEAL to Other LSA Alternatives
- 4 Discussion
- 5 Conclusion and Future Directions
- Acknowledgements
- References
- 4D Affect Detection: Improving Frustration Detection in Game-Based Learning with Posture-Based Temporal Data Fusion
- Abstract
- 1 Introduction
- 2 Related Work
- 3 TC3Sim Game-Based Learning Environment
- 4 Detecting Frustration with Posture-Based Temporal Data Fusion
- 4.1 Dataset
- 4.2 Temporal Feature Engineering
- 4.3 Feature Selection
- 4.4 Deep Neural Network Architecture
- 4.5 Data Fusion
- 5 Results
- 6 Conclusion
- Acknowledgements
- References
- Designing for Complementarity: Teacher and Student Needs for Orchestration Support in AI-Enhanced Classrooms
- 1 Introduction
- 2 Methods
- 2.1 Needs Validation Through Participatory Speed Dating
- 3 Results
- 3.1 Most Preferred Design Concepts
- 3.2 Least Preferred Design Concepts
- 4 Discussion, Conclusions, and Future Work
- References
- The Case of Self-transitions in Affective Dynamics
- Abstract
- 1 Introduction
- 2 L Statistics and Affect Dynamics Analysis
- 3 Analysis
- 3.1 Understanding How Removing Self-transitions Affect L Values
- 3.2 Redefining Chance L Value
- 4 Implications
- 5 Conclusion
- Acknowledgements
- References
- How Many Times Should a Pedagogical Agent Simulation Model Be Run?
- Abstract
- 1 Introduction
- 2 Related Work
- 2.1 Simulation Runs Within Simulation Research
- 2.2 Simulation Runs in AIED Research
- 3 SimDoc: Simulated Doctoral Program
- 4 Examining the Simulation Runs
- 4.1 Testing for an Adequate Number of Simulation Runs
- 4.2 Test of Stability in Simulation Output
- 4.3 Test of Variability Among Simulation Runs
- 5 Conclusion
- Acknowledgements
- References
- A Survey of the General Public's Views on the Ethics of Using AI in Education
- Abstract
- 1 Introduction
- 2 Legal and Ethical Considerations of AI in Education
- 2.1 Ethical Issues of AI in Education
- 2.2 The Impact of GDPR
- 3 Profiling in Learning Systems
- 3.1 Intelligent Tutoring System Approaches
- 3.2 Oscar CITS
- 3.3 Hendrix CITS
- 4 Case Study - Manchester Science Festival
- 4.1 Overview
- 4.2 Methods
- 4.3 Results and Discussion
- 5 Conclusion
- Acknowledgements
- References
- Promoting Inclusivity Through Time-Dynamic Discourse Analysis in Digitally-Mediated Collaborative Learning
- 1 Introduction
- 1.1 Discourse Dynamics, Gender Differences, and Group Composition in Online Interactions
- 1.2 Research Motivation
- 2 Current Study and Group Communication Analysis
- 2.1 Semantic-Based GCA Measures
- 3 Method
- 3.1 Participant
- 3.2 Procedure
- 3.3 Data Analysis
- 4 Result
- 5 Discussion
- 6 Conclusion
- References
- Evaluating Machine Learning Approaches to Classify Pharmacy Students' Reflective Statements
- Abstract
- 1 Introduction
- 2 Reflective Writing Analytics
- 3 Method
- 3.1 Dataset Description
- 3.2 Feature Extraction and Selection
- 3.3 Addressing the Problem of Class Imbalance
- 3.4 Model Selection and Evaluation
- 4 Results and Discussion
- 4.1 Classification Results and Discussion
- 4.2 Feature Importance Analysis and Discussion
- 5 Conclusion and Future Work
- References
- Comfort with Robots Influences Rapport with a Social, Entraining Teachable Robot
- Abstract
- 1 Introduction
- 2 Teachable Robot System
- 2.1 System
- 2.2 Multi-feature Paraverbal Entrainment as Convergence
- 2.3 Social Dialogue
- 3 Study
- 4 Results
- 4.1 Rapport
- 4.2 Learning
- 5 Discussion
- 6 Conclusion
- Acknowledgements
- References
- A Concept Map Based Assessment of Free Student Answers in Tutorial Dialogues
- 1 Introduction
- 2 Related Work
- 3 Concept Map Based Approach
- 3.1 Creation of Ideal Concept Maps
- 3.2 Automated Extraction of Student Concept Maps
- 3.3 Assessment System
- 4 Experiment and Results
- 4.1 Data
- 4.2 Experiments
- 4.3 Results and Discussions
- 5 Conclusion
- References
- Deep (Un)Learning: Using Neural Networks to Model Retention and Forgetting in an Adaptive Learning System
- 1 Introduction
- 2 Background
- 3 Forgetting Curve
- 4 Exploratory Data Analysis
- 5 Retention Models
- 6 Model Evaluation and Feature Importance
- 7 Discussion and Future Work
- References
- Checking It Twice: Does Adding Spelling and Grammar Checkers Improve Essay Quality in an Automated Writing Tutor?
- Abstract
- 1 Introduction
- 1.1 What About Spelling and Grammar?
- 1.2 The Current Study
- 2 Method
- 2.1 Participants
- 2.2 Design and Procedure
- 2.3 Writing Assessment and Scoring
- 3 Results
- 3.1 Analysis of Essay Improvement and Condition
- 3.2 Effects on Holistic Writing Quality and Grammar, Style, and Mechanics
- 3.3 Additional Benefits of Spelling and Grammar Feedback
- 3.4 Writing Subscores Unaffected by Spelling and Grammar Feedback
- 4 Discussion and Future Work
- 4.1 Incremental Improvements in Essay Quality
- 4.2 Directions for Future Research
- 4.3 Conclusion
- Acknowledgements
- References
- What's Most Broken? Design and Evaluation of a Tool to Guide Improvement of an Intelligent Tutor
- 1 Introduction
- 2 Relation to Prior Work
- 2.1 Software Reliability
- 2.2 Usability
- 2.3 Engagement, Off-Task Behavior and Gaming the System
- 3 Methodology
- 3.1 Organization of RoboTutor
- 3.2 Data Collection
- 3.3 Approach
- 4 Discoveries
- 5 Evaluation
- 5.1 Experiment Design
- 5.2 Experiment Results
- 6 Conclusion and Future Work
- References
- Reducing Mind-Wandering During Vicarious Learning from an Intelligent Tutoring System
- Abstract
- 1 Introduction
- 1.1 Theoretical Background and Motivation for Current Study
- 1.2 Current Study
- 2 Methods
- 2.1 GuruTutor Overview
- 2.2 Participants and Design
- 2.3 Materials and Procedure
- 3 Results and Discussion
- 3.1 How Often Did Participants' Mind-Wander?
- 3.2 Did Firsthand Student Expertise Influence Mind-Wandering in Secondhand Learners (Participants in Current Study)?
- 3.3 Did Firsthand Student Expertise Influence Learning?
- 3.4 Did Firsthand Student Expertise Influence Learning Through Mind-Wandering?
- 4 General Discussion and Conclusion
- 4.1 Main Findings
- 4.2 Limitations and Future Directions
- 4.3 Conclusion
- Acknowledgments
- References
- Annotated Examples and Parameterized Exercises: Analyzing Students' Behavior Patterns
- 1 Introduction
- 2 Related Work
- 3 System and Dataset
- 4 Modeling Student Behavior
- 4.1 Coding Student Behavior
- 4.2 Sequential Pattern Mining
- 4.3 Building Pattern Vectors
- 5 Behavior Stability Analysis
- 5.1 Randomized Analysis
- 5.2 Longitudinal Analysis
- 5.3 Complexity Analysis
- 6 Behavior Cluster Analysis
- 6.1 Pattern Analysis
- 6.2 Performance Analysis
- 7 Conclusions
- References
- Investigating the Effect of Adding Nudges to Increase Engagement in Active Video Watching
- Abstract
- 1 Introduction
- 2 Previous Work on AVW-Space
- 3 Adding Nudging to AVW-Space
- 3.1 Interactive Visualizations
- 3.2 Personalized Prompts
- 4 Experimental Design
- 5 Results
- 5.1 Do Nudges Foster Constructive Behavior?
- 5.2 What Features of AVW-Space Improve Students' Knowledge?
- 5.3 Do Students in the Two Conditions Differ in Their Opinions About the Usefulness of AVW-Space and Cognitive Load?
- 6 Conclusions
- Acknowledgements
- References
- Behavioural Cloning of Teachers for Automatic Homework Selection
- 1 Introduction
- 2 Related Work
- 3 Experiments
- 3.1 Data
- 3.2 Student Features
- 3.3 Implementation
- 3.4 Setting Individual Work
- 3.5 Modifications to Set Group Work
- 3.6 Baseline Policies
- 3.7 Evaluation
- 4 Results
- 5 Discussion
- 6 Conclusion
- References
- Integrating Students' Behavioral Signals and Academic Profiles in Early Warning System
- 1 Introduction
- 2 Related Works
- 2.1 Predicting Student Performance
- 2.2 Early Warning Systems
- 2.3 Overview of the Current Study
- 3 Methods
- 3.1 Data Source
- 3.2 Building Models
- 4 Results
- 4.1 Selecting Behavioral Variables
- 4.2 Integrating Student Profile Information
- 4.3 Predictive Modeling: Weekly Performance
- 5 Conclusion and Discussion
- References
- Predicting Multi-document Comprehension: Cohesion Network Analysis
- Abstract
- 1 Introduction
- 1.1 Comprehension of Multiple Documents
- 1.2 Assessing and Evaluating Comprehension
- 1.3 Cohesion Network Analysis
- 2 Method
- 2.1 Dataset
- 2.2 Multi-document Cohesion Network Analysis
- 2.3 Classification Methods
- 3 Results
- 3.1 Selecting the Best Semantic Measures
- 3.2 Features Filtering
- 3.3 Predicting Reading Comprehension
- 4 Conclusions and Future Work
- Acknowledgments
- References
- Student Network Analysis: A Novel Way to Predict Delayed Graduation in Higher Education
- 1 Introduction
- 2 Related Work
- 3 Our Dataset
- 4 Proposed Prediction Method
- 4.1 Academic Features
- 4.2 Student Network Features
- 4.3 Fix-Point Features
- 4.4 Experiments
- 5 Key Observations, Future Work and Conclusions
- References
- Automatic Generation of Problems and Explanations for an Intelligent Algebra Tutor
- 1 Introduction
- 2 Background
- 2.1 Modeling Learning Domains
- 2.2 Explanation Generation
- 2.3 Problem Generation
- 3 Implementation Approach
- 3.1 Modeling Algebra in ASP
- 3.2 Problem and Solution Generation
- 3.3 Explanation Generation
- 3.4 Misapplied Rules
- 4 Formative Evaluation
- 4.1 Proof-of-Concept Implementation
- 4.2 Mechanical Turk Study
- 4.3 Student Study
- 5 Discussion and Conclusion
- References
- Generalizability of Methods for Imputing Mathematical Skills Needed to Solve Problems from Texts
- 1 Introduction
- 2 Replicability
- 2.1 Text Representation and Preprocessing
- 2.2 Replicated Model
- 2.3 Replicability Result
- 2.4 Does It Generalize?
- 2.5 Causes of Overfitting
- 3 Towards Generalizability
- 3.1 Near-Identical Problems
- 3.2 HTML Element and Formatting
- 4 Results
- 5 Conclusion
- 6 Future Work
- References
- Using Machine Learning to Overcome the Expert Blind Spot for Perceptual Fluency Trainings
- Abstract
- 1 Introduction
- 2 Theoretical Background
- 2.1 Inductive Learning of Perceptual Fluency
- 2.2 Perceptual-Fluency Trainings
- 2.3 Machine-Learned Sequences for Perceptual-Fluency Trainings
- 3 Research Questions
- 4 Methods
- 4.1 Participants
- 4.2 Chem Tutor: An ITS for Undergraduate Chemistry
- 4.3 Experimental Design
- 4.4 Measures
- 4.5 Procedure
- 5 Results
- 5.1 Prior Checks
- 5.2 Effects of Sequence
- 6 Discussion
- Acknowledgements
- References
- Disentangling Conceptual and Embodied Mechanisms for Learning with Virtual and Physical Representations
- Abstract
- 1 Introduction
- 2 Theoretical Background
- 2.1 Learning with Interactive Visual Representations
- 2.2 Virtual vs Physical Representation Modes
- 3 Research Questions and Hypotheses
- 3.1 Concept A: Electrons Randomly Fill Equal-Energy Orbitals
- 3.2 Concept B: Up and Down Spins Have Equal Energy
- 3.3 Concept C: Spins Are Rotational Movements
- 4 Methods
- 4.1 Participants
- 4.2 Experimental Design
- 4.3 Materials
- 4.4 Procedure
- 5 Results
- 5.1 Prior Checks
- 5.2 Effects of Representation Mode and Movement
- 6 Discussion and Conclusion
- Acknowledgements
- References
- Adaptive Support for Representation Skills in a Chemistry ITS Is More Effective Than Static Support
- Abstract
- 1 Introduction
- 2 Theoretical Background
- 2.1 Sense-Making Skills
- 2.2 Perceptual Fluency
- 2.3 Combining Support for Sense-Making Skills and Perceptual Fluency
- 3 Experiment
- 3.1 Chem Tutor: An ITS for Undergraduate Chemistry
- 3.2 Development of the Adaptive Assignment Algorithm
- 3.3 Methods
- 3.4 Results
- 4 Discussion and Conclusion
- Acknowledgements
- References
- Confrustion in Learning from Erroneous Examples: Does Type of Prompted Self-explanation Make a Difference?
- Abstract
- 1 Introduction
- 2 Methods
- 2.1 Participants
- 2.2 Materials
- 2.3 Procedure
- 2.4 Affect Detection
- 3 Results
- 4 Discussion
- References
- Modeling Collaboration in Online Conversations Using Time Series Analysis and Dialogism
- Abstract
- 1 Introduction
- 2 Method
- 2.1 Corpora
- 2.2 Method
- 3 Results and Discussions
- 4 Conclusions and Future Work
- Acknowledgments
- References
- Improving Short Answer Grading Using Transformer-Based Pre-training
- 1 Introduction
- 2 Related Work
- 2.1 Hand-Crafted Features
- 2.2 Deep Learning Approaches
- 3 BERT for Short Answer Grading
- 3.1 BERT Model Architecture
- 4 Experiments
- 4.1 Pre-training Setup
- 4.2 Fine-Tuning Setup
- 4.3 Results and Analysis
- 5 Conclusion
- References
- Uniform Adaptive Testing Using Maximum Clique Algorithm
- 1 Introduction
- 2 Computerized Adaptive Testing Based on Item Response Theory
- 2.1 Item Response Theory
- 2.2 Fisher Information
- 2.3 Computerized Adaptive Testing
- 2.4 Constrained CAT with Item Exposure Control
- 3 Uniform Adaptive Testing Using Maximum Clique Algorithm
- 3.1 Uniform Partitioning of the Item Pool
- 3.2 Adaptive Item Selection from an Item Group
- 4 Numerical Evaluation
- 4.1 Simulation Experiment
- 4.2 Experiment Conducted Using Actual Data
- 5 Conclusions
- References
- Rater-Effect IRT Model Integrating Supervised LDA for Accurate Measurement of Essay Writing Ability
- 1 Introduction
- 2 Data
- 3 Item Response Theory
- 4 Topic Model
- 5 Supervised Topic Model
- 6 Proposed Model
- 6.1 Parameter Estimation Using MCMC
- 6.2 Ability Estimation from Text Data and Automated Essay Scoring
- 7 Experiments Using Actual Data
- 7.1 Evaluation of Ability Measurement Accuracy
- 7.2 Ability Measurement Accuracy Without Rating Data
- 7.3 Accuracy of Automated Essay Scoring
- 8 Conclusion
- References
- Collaboration Detection that Preserves Privacy of Students' Speech
- Abstract
- 1 Introduction
- 2 Prior Work on Speech-Based Collaboration Detection
- 3 Data Collection
- 3.1 Task: Collaborative Writing
- 3.2 Technology, Participants and Duration
- 3.3 Raw Data Collection
- 3.4 Coding Categories
- 4 Analysis Methods
- 4.1 Audio Processing and Extraction of Audio Logs
- 4.2 Segmentation
- 4.3 Human Coding
- 4.4 Feature Extraction
- 4.5 Feature Selection
- 5 Results
- 5.1 Binary Classifier Focused on Cooperation
- 5.2 Binary Classifier Focused on Interaction
- 5.3 Binary Classifier Focused on Other Category
- 5.4 Ternary Classifier
- 6 Discussion and Conclusion
- Acknowledgements
- References
- How Does Order of Gameplay Impact Learning and Enjoyment in a Digital Learning Game?
- Abstract
- 1 Introduction
- 2 Background
- 2.1 The Decimal Point Game
- 2.2 Related Work
- 3 Context
- 4 Results
- 4.1 Game Sequence Clustering
- 4.2 Post Analysis
- 5 Discussion
- 6 Conclusion
- Acknowledgements
- References
- Analyzing Students' Design Solutions in an NGSS-Aligned Earth Sciences Curriculum
- 1 Introduction
- 2 Engineering Design and the K-12 Curricula
- 3 Methods
- 3.1 The Engineering Design Environment
- 3.2 Playground Design Criteria and Scoring
- 3.3 Assessment of Integrated Science and Engineering Proficiency
- 4 Results and Discussions
- 4.1 Learning Gains from the Curriculum Unit
- 4.2 Playground Design Behaviors and Design Scores
- 4.3 Correlation Analyses
- 4.4 A Case Description
- 5 Conclusions
- References
- Hierarchical Reinforcement Learning for Pedagogical Policy Induction
- 1 Introduction
- 2 Background and Related Work
- 2.1 Previous Research on Applying RL to ITSs
- 2.2 WE, PS and FWE
- 3 Policy Induction
- 3.1 GP-Based Approach for Immediate Reward Inference
- 3.2 An Offline, Off-policy GP-Based HRL for Policy Induction
- 3.3 DQN for Policy Induction
- 4 Empirical Experiment
- 5 Results
- 6 Conclusion and Discussion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.