This document is a syllabus for a Deep Reinforcement Learning course offered at Harvard Extension School in Spring 2021. The course will be taught online and cover topics such as Markov Decision Processes, dynamic programming, Monte Carlo methods, temporal-difference learning, deep learning, value-based deep RL, policy-based deep RL and model-based deep RL. Students will complete homework assignments, quizzes, a midterm exam and final exam in Python. The course aims to provide students with skills in building optimal neural networks for reinforcement learning tasks.
Kovanović et al. 2017 - developing a mooc experimentation platform: insight...Vitomir Kovanovic
LAK'17 Conference paper presentation:
Abstract:
In 2011, the phenomenon of MOOCs had swept the world of education and put online education in the focus of the public discourse around the world. Although researchers were excited with the vast amounts of MOOC data being collected, the benefits of this data did not stand to the expectations due to several challenges. The analyses of MOOC data are very time-consuming and labor-intensive, and require a highly advanced set of technical skills, often not available to the education researchers. Because of this MOOC data analyses are rarely done before the courses end, limiting the potential of data to impact the student learning outcomes and experience.
In this paper we introduce MOOCito (MOOC intervention tool), a user-friendly software platform for the analysis of MOOC data, that focuses on conducting data-informed instructional interventions and course experimentations. We cover important design principles behind MOOCito and provide an overview of the trends in MOOC research leading to its development. Although a work-in-progress, in this paper, we outline the prototype of MOOCito and the results of a user evaluation study that focused on system’s perceived usability and ease-of-use. The results of the study are discussed, as well as their practical implications.
Broadening the scope of a Maths module for student Technology teachersUofGlasgowLTU
In this paper we will discuss the use of Moodle 2.4 Activities to enhance student learning in an undergraduate first year mathematics module. We begin by setting out the reasons for redesigning an existing course by using Moodle 2.4, and our reasons for selecting the activities that we added to the course. We present examples of student engagement with the course and end with time for questions from the audience.
Over the last three sessions, we have redeveloped a Maths module for student Technology teachers to provide an experience that is more relevant to their intended career. The most recent version of this was written this year by using Moodle 2.4, forums, wikis, the “External Tool” facility and Mahara.
Previously, the module was essentially a revision and levelling-up course, which was intended to ensure that students’ mathematical capability was sufficient to cope with the rest of their course. Students were required to complete ten tests covering topics from numeracy to differentiation and complex numbers, and attendance was mandatory only until they had done so. This led to a “race to finish” attitude, which had the more able students leaving the class early in the second semester and the less able battling on with completing the tests as their only goal. Understandably, engagement was minimal, the module was regarded as a chore and its relevance to the remainder of their course was poorly understood.
Realising that the students need to learn to take the teacher’s viewpoint, we introduced a “topics wiki” in which groups of students collaborate to provide additional explanations and resources around the course content. The efforts so far are very worthwhile and will be of use to those with less experience of Maths and to future students. Students are encouraged to discuss the resources during class time, and beyond. Some of the more able students are helping their classmates already, and we are actively encouraging this. We are also encouraging students to use these group wikis to build personal e-portfolios using Mahara, and this will be reinforced next semester when students participate in group projects.
Students are more engaged this year than in previous years, and we believe that this is because we have made better use of the functionality of Moodle, and are scaffolding student learning as they progress through the course.
Presentation by Francesca Amenduni, Ph.D. Student, University of Roma Tre, EDEN NAP member, at the 2019 European Distance Learning Week's third-day webinar on "Future perspective in open routes: the quality and assessment dimension?" - 13 November 2019
Recording of the discussion is available: https://eden-online.adobeconnect.com/p8i31ynv7v28/ & https://www.youtube.com/watch?v=7yb8ekFP3ps
Kovanović et al. 2017 - developing a mooc experimentation platform: insight...Vitomir Kovanovic
LAK'17 Conference paper presentation:
Abstract:
In 2011, the phenomenon of MOOCs had swept the world of education and put online education in the focus of the public discourse around the world. Although researchers were excited with the vast amounts of MOOC data being collected, the benefits of this data did not stand to the expectations due to several challenges. The analyses of MOOC data are very time-consuming and labor-intensive, and require a highly advanced set of technical skills, often not available to the education researchers. Because of this MOOC data analyses are rarely done before the courses end, limiting the potential of data to impact the student learning outcomes and experience.
In this paper we introduce MOOCito (MOOC intervention tool), a user-friendly software platform for the analysis of MOOC data, that focuses on conducting data-informed instructional interventions and course experimentations. We cover important design principles behind MOOCito and provide an overview of the trends in MOOC research leading to its development. Although a work-in-progress, in this paper, we outline the prototype of MOOCito and the results of a user evaluation study that focused on system’s perceived usability and ease-of-use. The results of the study are discussed, as well as their practical implications.
Broadening the scope of a Maths module for student Technology teachersUofGlasgowLTU
In this paper we will discuss the use of Moodle 2.4 Activities to enhance student learning in an undergraduate first year mathematics module. We begin by setting out the reasons for redesigning an existing course by using Moodle 2.4, and our reasons for selecting the activities that we added to the course. We present examples of student engagement with the course and end with time for questions from the audience.
Over the last three sessions, we have redeveloped a Maths module for student Technology teachers to provide an experience that is more relevant to their intended career. The most recent version of this was written this year by using Moodle 2.4, forums, wikis, the “External Tool” facility and Mahara.
Previously, the module was essentially a revision and levelling-up course, which was intended to ensure that students’ mathematical capability was sufficient to cope with the rest of their course. Students were required to complete ten tests covering topics from numeracy to differentiation and complex numbers, and attendance was mandatory only until they had done so. This led to a “race to finish” attitude, which had the more able students leaving the class early in the second semester and the less able battling on with completing the tests as their only goal. Understandably, engagement was minimal, the module was regarded as a chore and its relevance to the remainder of their course was poorly understood.
Realising that the students need to learn to take the teacher’s viewpoint, we introduced a “topics wiki” in which groups of students collaborate to provide additional explanations and resources around the course content. The efforts so far are very worthwhile and will be of use to those with less experience of Maths and to future students. Students are encouraged to discuss the resources during class time, and beyond. Some of the more able students are helping their classmates already, and we are actively encouraging this. We are also encouraging students to use these group wikis to build personal e-portfolios using Mahara, and this will be reinforced next semester when students participate in group projects.
Students are more engaged this year than in previous years, and we believe that this is because we have made better use of the functionality of Moodle, and are scaffolding student learning as they progress through the course.
Presentation by Francesca Amenduni, Ph.D. Student, University of Roma Tre, EDEN NAP member, at the 2019 European Distance Learning Week's third-day webinar on "Future perspective in open routes: the quality and assessment dimension?" - 13 November 2019
Recording of the discussion is available: https://eden-online.adobeconnect.com/p8i31ynv7v28/ & https://www.youtube.com/watch?v=7yb8ekFP3ps
Course-Adaptive Content Recommender for Course AuthoringPeter Brusilovsky
Developing online courses is a complex and time-consuming
process that involves organizing a course into a sequence of topics and
allocating the appropriate learning content within each topic. This task
is especially difficult in complex domains like programming, due to the
incremental nature of programming knowledge, where new topics extensively
build upon domain concepts that were introduced in earlier lessons.
In this paper, we propose a course-adaptive content-based recommender
system that assists course authors and instructors in selecting the most
relevant learning material for each course topic. The recommender system
adapts to the deep prerequisite structure of the course as envisioned
by a specific instructor, while unobtrusively deducing that structure from
problem-solving examples that the instructor uses to present course concepts.
We assessed the quality of recommendations and examined several
aspects of the recommendation process by using three datasets collected
from two different courses.While the presented recommender system was
built for the domain of introductory programming, our course-adaptive
recommendation approach could be used in a variety of other domains.
TLC2016 - Peer Review, Peer Assessment, and Peer Feedback methods based on Bl...BlackboardEMEA
Presenter: Hubert Nachtegaele
Organisation: Universiteit Antwerpen
Description: Our teaching staff asks support for types of “Self and Peer Assessment” which are not possible with the S&PA tool incorporated in Bb Learn.
Our Blackboard Support Team tries to support the desired types of S&PA by creative combinations solely of Bb Learn Course Tools, without using external tools (except Excel). In this session we will show how we realize this for different types of S&PA: “Groups reviewing assignments of other groups”, “Students assessing their peers and themselves within a group”, “Peer Reviewing using a rubric”, and "Anonymous Peer Feedback for oral presentations"
VII Jornadas eMadrid "Education in exponential times". Mesa redonda eMadrid L...eMadrid network
VII Jornadas eMadrid "Education in exponential times". Mesa redonda eMadrid Learning Analytics. "The contributions of Data Visualization & Learning Analytics for Online Courses". Ruth Cobos Pérez. 04/07/2017.
Track 12. Educational Innovation
Authors: Ricardo Castedo, Anastasio P. Santos, Lina M. López, María Chiquito and Oriol Borrás-Gené
https://youtu.be/wfipCCWhR-Q
Web-based Virtual Reality development in classroom: From learner's perspectivesVinhNguyen628
Virtual Reality (VR) content development tools are in continuous production by both enthusiastic researchers and software development companies. Yet, learners could benefit from participating in this development, not only for learning vital programming skills, but also skills in creativity and collaboration. Web-based VR (WebVR) has emerged as a platform-independent framework that permits individuals (with little to no prior programming experience) to create immersive and interactive VR applications. Yet, the success of WebVR relies on students' technological acceptance, the intersectionality of perceived utility and ease of use. In order to determine the effectiveness of the emerging tool for learners of varied experience levels, this paper presents a case study of 38 students who were tasked with developing WebVR 'dream' houses. Results showed that students were accepting of the technology by not only learning and implementing WebVR in a short time (one month), but were also capable of demonstrating creativity and problem-solving skills with classroom supports (i.e., pre-project presentations, online discussions, exemplary projects, and TA support). Results as well as recommendations, lessons learned, and further research are addressed
Course-Adaptive Content Recommender for Course AuthoringPeter Brusilovsky
Developing online courses is a complex and time-consuming
process that involves organizing a course into a sequence of topics and
allocating the appropriate learning content within each topic. This task
is especially difficult in complex domains like programming, due to the
incremental nature of programming knowledge, where new topics extensively
build upon domain concepts that were introduced in earlier lessons.
In this paper, we propose a course-adaptive content-based recommender
system that assists course authors and instructors in selecting the most
relevant learning material for each course topic. The recommender system
adapts to the deep prerequisite structure of the course as envisioned
by a specific instructor, while unobtrusively deducing that structure from
problem-solving examples that the instructor uses to present course concepts.
We assessed the quality of recommendations and examined several
aspects of the recommendation process by using three datasets collected
from two different courses.While the presented recommender system was
built for the domain of introductory programming, our course-adaptive
recommendation approach could be used in a variety of other domains.
TLC2016 - Peer Review, Peer Assessment, and Peer Feedback methods based on Bl...BlackboardEMEA
Presenter: Hubert Nachtegaele
Organisation: Universiteit Antwerpen
Description: Our teaching staff asks support for types of “Self and Peer Assessment” which are not possible with the S&PA tool incorporated in Bb Learn.
Our Blackboard Support Team tries to support the desired types of S&PA by creative combinations solely of Bb Learn Course Tools, without using external tools (except Excel). In this session we will show how we realize this for different types of S&PA: “Groups reviewing assignments of other groups”, “Students assessing their peers and themselves within a group”, “Peer Reviewing using a rubric”, and "Anonymous Peer Feedback for oral presentations"
VII Jornadas eMadrid "Education in exponential times". Mesa redonda eMadrid L...eMadrid network
VII Jornadas eMadrid "Education in exponential times". Mesa redonda eMadrid Learning Analytics. "The contributions of Data Visualization & Learning Analytics for Online Courses". Ruth Cobos Pérez. 04/07/2017.
Track 12. Educational Innovation
Authors: Ricardo Castedo, Anastasio P. Santos, Lina M. López, María Chiquito and Oriol Borrás-Gené
https://youtu.be/wfipCCWhR-Q
Web-based Virtual Reality development in classroom: From learner's perspectivesVinhNguyen628
Virtual Reality (VR) content development tools are in continuous production by both enthusiastic researchers and software development companies. Yet, learners could benefit from participating in this development, not only for learning vital programming skills, but also skills in creativity and collaboration. Web-based VR (WebVR) has emerged as a platform-independent framework that permits individuals (with little to no prior programming experience) to create immersive and interactive VR applications. Yet, the success of WebVR relies on students' technological acceptance, the intersectionality of perceived utility and ease of use. In order to determine the effectiveness of the emerging tool for learners of varied experience levels, this paper presents a case study of 38 students who were tasked with developing WebVR 'dream' houses. Results showed that students were accepting of the technology by not only learning and implementing WebVR in a short time (one month), but were also capable of demonstrating creativity and problem-solving skills with classroom supports (i.e., pre-project presentations, online discussions, exemplary projects, and TA support). Results as well as recommendations, lessons learned, and further research are addressed
OutlineWhat will your programinitiativecourse do What are .docxgerardkortney
Outline:
What will your program/initiative/course do? What are the activities that participants in your program will do? How long will they last?
These courses offered to student attending local inner city schools will give them relevant knowledge related to the STEM field
Courses Offered include:
CSCI 1001 Computer Fundamentals (A, SP, SU) 2 credits
CSCI 1001 introduces the inexperienced computer user to the fundamentals of computer terminology, hardware, software, windows operating system, directories, folders, files, copy/paste functions, naming conventions and setting passwords. Additional topics covered include the World Wide Web, the Internet, search engines and Blackboard.
Lecture: 1 hour - Lab: 2 hours Lab fee: $6.00
CSCI 1102 Intermediate Excel & Access (SP) 3 credits
CSCI 1102 is a continuation of CSCI 1101, incorporating Intermediate concepts and techniques used in spreadsheets and database software.
Examples: financial functions, data tables, amortization schedules, working with multiple worksheets, macros, database queries, reports, switchboards, pivot tables and charts, and using SQL. Project management and HTML concepts will be introduced. Students will learn how to use these tools for analysis and decision making.
Lecture: 2 hours - Lab: 2 hours
Prerequisite: CSCI 1101 Lab fee: $2.00
MATH 1099 Bridge to College Math (A, SP, SU)
3 credits The topics contained in DEV 0114, MATH 1050, and MATH 1075 will be delivered in a modularized format using technology, allowing students to begin at the appropriate level based on course placement and allowing them to move through as many modules and courses as they can within the time limits of the course. This modularized, mastery approach will pre-test, provide a prescriptive study plan, and post-test students from one module to the next. Emphasis will be placed on individualized pace with a greater time period of active learning. At the end of the course, based on proficiency of the series of modules associated with one or more courses, students will earn a grade of “S” for satisfactory progress and gain permission to enter subsequent courses in their plan of study.
Lab: 6 hours
Prerequisite: Placement score which allows for DEV 0114 or MATH 1050 or MATH 1075 registration Lab fee: $7.00
MATH 1050 Elementary Algebra (A, SP, SU)
5 credits This is the first course of a two-semester sequence. It covers the study of the real number system including properties of real numbers, order of operations, operations on algebraic expressions, solving linear equations and inequalities in one variable, the rectangular coordinate system, graphs of linear equations and inequalities in two variables, systems of equations and inequalities in two variables, applications and modeling, properties of exponents, scientific notation, polynomial arithmetic, factoring, solving polynomial equations. Course also emphasizes applications and activities to build skills in problem solving. Not open to students with cr.
This presentation will outline an effective model for a Hybrid Statistics course. The course continues to be very successful, incorporating on-line instruction, testing, blogs, and, above all, a data analysis project based on real up-to-date easily understood data.The course follows a project driven trajectory motivating students
to engage more aggressively in the class and rise up to the challenge of writing an original research paper. Obstacles, benefits and successes of this endeavor will be addressed.
Invited to speak again at the Marist College Summer Series. Spoke about open source in universities, introduced Red Hat's "Open Source University" program and coursework.
ISSC362Course SummaryCourse ISSC362 Title IT SecuritTatianaMajor22
ISSC362
Course Summary
Course : ISSC362 Title : IT Security: Attack & Defense
Length of Course : 8 Faculty :
Prerequisites : N/A Credit Hours : 3
Description
Course Description:
This course examines the techniques and technologies for penetration of networks, detection of attacks, and
prevention of attacks. This course addresses the techniques, the technologies, and the methodologies used
by cyber intruders (hackers) to select a target and launch an attack. Students will gain insight into the motives
and desired goals of hackers as well as effective tools and techniques used as countermeasures ensuring
data assets remain secure. This course focuses on techniques and technologies to detect such attacks even
while the attack is in progress; early detection enables the administrator to track the movements of the
hacker and to discover the intent and goals of the hacker. This course assesses the various
countermeasures to keep the system out of the “sights” of the hacker and to keep the hacker out of the
perimeter of the target network. This course also explores the laws and the legal considerations in
prosecuting computer crime.
Course Scope:
This course will allow students to see how attacks target networks and the methodology they follow. Students
will also learn how to respond to hacking attacks and how to fend them off. With the help of the experts in the
Information Systems Security and Assurance Series, the book will provide examples of information security
concepts and procedures are presented throughout the course.
Page: 1 of 8 Date: 6/21/2020 3:01:15 AM
Objectives
After successfully completing this course, you will be able to:
1. Show how attackers map organizations
2. Describe common port scanning techniques
3. Identify some of the tools used to perform enumeration
4. Explain the significance of wireless security
5. List the issues facing Web servers
6. Describe the characteristics of malware
7. List the ways of detecting Trojans
8. Describe the process of DoS attacks
9. Describe the benefits of automated assessment tools
10. List the components of incident response
11. List the detective methods of IDS
Outline
Week 1: Course Overview Getting Started Introduction to Ethical Hacking
Activities
Reading: Chapters 1, 2, 3 and 4
PPT Review: Lessons 1, 2 and 3 (Physical Security)
Week 1 Discussion
Lab
Week 2: Footprinting, Port Scanning and Enumeration
Activities
Reading: Chapters 5, 6, and 7
PPT Review: Lessons 3 (Footprinting) and 4
Week 2 Discussion
Lab
Week 3: Web and Database Attacks
Activities
Reading: Chapter 9
PPT Review: Lesson 6
Week 3 Discussion
Lab
Page: 2 of 8 Date: 6/21/2020 3:01:15 AM
Week 4: Malware, Worms, Viruses, Trojans and Backdoors
Activities
Reading: Chapters 10 and 11
PPT Review: Lesson 7
Week 4 Discussion
Lab
Week 5: Network Traffic Analysis
Activities
Reading: Chapters 12 and 13
PPT Review: Lesson 8
Week 5 Discussion
Midterm
Lab
Week 6: Wireless Vulnerabilities
Act ...
This complete outline of Res 1-Methods of Research indents to give an overview of the course for the whole semester with 54 hours equal to 3 units credit. Lessons are excluded in this outline and will be presented per meeting of 1.5 hours twice a week meeting.
1 Saint Leo University GBA 334 Applied Decision.docxaryan532920
1
Saint Leo University
GBA 334
Applied Decision Methods for Business
Course Description:
This course explores the use of applied quantitative techniques to aid in business-oriented decision
making. Emphasis is on problem identification and formulation with application of solution techniques and
the interpretation of results. Included are probability theory; decision making under certainty, risk and
uncertainty; utility theory; forecasting; inventory control; PERT/CPM; queuing theory; and linear
programming.
Prerequisite:
MAT 201
Textbook:
Saint Leo University. (2013), Quantitative analysis (custom). Boston, MA: Pearson Learning
Solution
s.
eBook with print upgrade option – ISBN: 978-1-269-86314-8
You will access the eBook via a link in the Course Home menu, where you can purchase the print
upgrade option.
Software
The use of statistical software is a required component in this course. It is expected that you already have
a basic understanding of computers and Microsoft Excel. In-depth training is provided during the course
on the appropriate use of the following packages:
TreePlan-Student-179 Excel Add In
Excel QM, version 4
POM QM, version 4
Analysis Tool Pack for Microsoft Excel must be activated
To access the information needed to install the software, click the Software Installation Information link
located under Resources in the course menu.
Learning Outcomes:
At the completion of the course you should be familiar with several decision methods of decision-making
in a business environment. You will find that almost every type of problem to which you will be exposed in
the business world has been explored and methods of solving them have been devised. You should be
able to apply these methods to the real-world situations in which you will one day find yourself. The skills
developed during this class include:
1. Explain the key attributes and differences between the normal, standard normal, and binomial
distribution of variables.
2. Identify and explain the underlying assumptions, key variables, theoretical basis, and solution
techniques for the following decision-making problems:
a. Decision Analysis
b. Probability Theory and Analysis
c. Regression Analysis
d. Forecasting Methods
e. Inventory Control Methods
f. Project Management (including PERT/CPM)
g. Network Models
h. Queuing Theory
i. Linear Programming Approaches and the Transportation and Assignment Special Cases
j. Statistical Process Control
2
3. Formulate and execute a solution to a variety of decision-making problems using computer
software.
4. Identify, explain, and interpret the key areas of computer output for the various decision-making
problems.
5. Apply one of the approaches covered in class to a real-world issue and present the findings.
6. VALUES OUTCOME: Demonstrate the core value of excellence by adequately preparing for
each class session, actively participating in cl ...
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
CFD Simulation of By-pass Flow in a HRSG module by R&R Consult.pptxR&R Consult
CFD analysis is incredibly effective at solving mysteries and improving the performance of complex systems!
Here's a great example: At a large natural gas-fired power plant, where they use waste heat to generate steam and energy, they were puzzled that their boiler wasn't producing as much steam as expected.
R&R and Tetra Engineering Group Inc. were asked to solve the issue with reduced steam production.
An inspection had shown that a significant amount of hot flue gas was bypassing the boiler tubes, where the heat was supposed to be transferred.
R&R Consult conducted a CFD analysis, which revealed that 6.3% of the flue gas was bypassing the boiler tubes without transferring heat. The analysis also showed that the flue gas was instead being directed along the sides of the boiler and between the modules that were supposed to capture the heat. This was the cause of the reduced performance.
Based on our results, Tetra Engineering installed covering plates to reduce the bypass flow. This improved the boiler's performance and increased electricity production.
It is always satisfying when we can help solve complex challenges like this. Do your systems also need a check-up or optimization? Give us a call!
Work done in cooperation with James Malloy and David Moelling from Tetra Engineering.
More examples of our work https://www.r-r-consult.dk/en/cases-en/
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Welcome to WIPAC Monthly the magazine brought to you by the LinkedIn Group Water Industry Process Automation & Control.
In this month's edition, along with this month's industry news to celebrate the 13 years since the group was created we have articles including
A case study of the used of Advanced Process Control at the Wastewater Treatment works at Lleida in Spain
A look back on an article on smart wastewater networks in order to see how the industry has measured up in the interim around the adoption of Digital Transformation in the Water Industry.
1. CSCI S-89C Deep Reinforcement Learning
Syllabus Spring 2021
Lectures: Online web conference, Wednesdays, 7:40-9:40 pm
Lectures will be live-streamed with the video being available via the course website within 24 hours.
Instructor: Dr. Dmitry Kurochkin, Senior Research Analyst, Harvard University
E-mail: dkurochkin@fas.harvard.edu
Website: https://canvas.harvard.edu/courses/81664
Office Hours: By request
Teaching Fellows: TBA e-mail: TBA
Prerequisites:
Introductory probability and statistics, multivariate calculus equivalent to MATH E-21a, and profi-
ciency in Python programming equivalent to CSCI E-7.
Note on the prerequisites:
We will be formulating value (cost) functions and performing optimization. Students are expected to be
comfortable taking derivatives. Basic knowledge of probability theory (in particular, conditional proba-
bility distributions and conditional expectations) is necessary. Understanding matrix vector operations
and notation is helpful but not required. All coding exercises are performed in Python. Students are
required to take a short pretest at the beginning of the course. The pretest score will not count toward
the final grade but will help you understand whether your background in calculus, probability theory,
as well as command of coding positions you for success in this course.
Text:
Richard Sutton and Andrew Barto, Reinforcement Learning: An Introduction, 2nd ed.
ISBN: 978-0-262-03924-6
Electronic copy of the book is available at the author’s webpage (under “Full Pdf”)
http://incompleteideas.net/book/the-book-2nd.html
Optional reading:
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016
ISBN: 978-0-262-03561-3
HTML version of the book is available at http://www.deeplearningbook.org
Course Description:
This course introduces Deep Reinforcement Learning (RL), one of the most modern techniques of ma-
chine learning. Deep RL has attracted the attention of many researches and developers in recent years
due to its wide range of applications in a variety of fields such as robotics, robotic surgery, pattern
recognition, diagnosis based on medical image, treatment strategies in clinical decision making, person-
alized medical treatment, drug discovery, speech recognition, computer vision, and natural language
processing. Deep RL is often seen as the third area of machine learning, in addition to supervised and
unsupervised algorithms, in which learning of an agent occurs as a result of its own actions and inter-
action with the environment. Generally, such learning processes do not need to be guided externally,
but it has been difficult until recently to use RL ideas practically. This course primarily focuses on
problems that emerge in healthcare and life science applications.
Tentative List of Topics:
I. Reinforcement Learning (RL)
◦ Markov Decision Processes (MDP): Value Functions and Policies
1
2. ◦ Dynamic Programming (DP): Bellman Equation
◦ Monte Carlo (MC) Methods
◦ Temporal-difference (TD) Prediction and Control: SARSA and Q-learning
◦ n-step TD
◦ Approximation Methods: Stochastic-gradient, Semi-gradient TD Update, Least-squares TD
II. Deep Learning
◦ Neural Networks (NN): Classification & Regression
◦ Training NNs: Backpropagation
◦ Tuning NNs: Regularization
◦ Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN)
III. Deep RL
◦ Value-based Deep RL: Q-network
◦ Policy-based Deep RL: REINFORCE
◦ Asynchronous Methods for Deep RL: Advantage Actor-Critic (A2C)
◦ Model-based Deep RL
Homework:
Except when especially noted, homework assignments will be due each Sunday. The assignments will
be posted on Canvas website and will consist of series of programming exercises (solutions should be
implemented in Python) as well as analytical problems (knowledge of calculus and probability theory
should suffice) that help students enhance their understanding of the underlying theory. Solutions to
the programming exercises should be submitted via Canvas in a form of a single .ipynb (Jupyter Note-
book) file. The solutions to the theoretical problems should be submitted in a form of a single PDF
file.
Note on the deadline and penalty:
Solutions to the assignments submitted later than 1, 2, 3, 4, and 5 days after the due date will be
penalized by 10%, 20%, 30%, 40%, and 100%, respectively. In case you need an extension, please
coordinate with the instructor prior to the due day.
Quizzes:
An online quiz will be due before each class, unless announced otherwise. The quiz will consist of ap-
proximately 5 basic questions on understanding of studied principals. No late quizzes will be allowed.
Midterm Exam:
The midterm exam will be released on March 10 (no lecture on March 10) and due March 17 at 7:40
pm (Eastern Time). The test will be similar to Homework exercises but cover topics studied up to this
date. Late midterm will not be accepted.
Final:
The final examination will be due at 11:59 pm (Eastern Time) on May 12 (no lecture on May 12). The
exam will be cumulative covering all topics studied. Late final will not be accepted.
Attendance:
Regular attendance (whether on campus or online) is expected but will not be taken. Recorded lectures
will be available via the course website within 24 hours after the lecture.
2
3. Participation:
Although no credit is allocated for participation, everyone is encouraged to constructively participate
in class by asking relevant questions. It is important that you check the e-mail registered with Canvas
regularly and monitor course announcements and also participate in discussions on Piazza, the fo-
rum available at https://piazza.com/class/kh5mr9vj75c2ah. All technical and data science related
questions will be discussed on Piazza.
Grading:
The semester average is calculated using the formula:
Grade = 0.25 · Homework + 0.20 · Quizzes + 0.25 · Midterm + 0.30 · Final
Student Learning Objectives:
◦ proficiency in building optimal NNs using Python
◦ understanding of RL including MDP, Bellman equation, and optimal policy
◦ firm understanding of Deep RL and getting comfortable with approximation methods used in
conjunction with RL
◦ hands-on experience on estimating the optimal policy and value functions
Academic Integrity:
You are responsible for understanding Harvard Extension School policies on academic integrity (www.
extension.harvard.edu/resources-policies/student-conduct/academic-integrity) and how to
use sources responsibly. Not knowing the rules, misunderstanding the rules, running out of time, sub-
mitting the wrong draft, or being overwhelmed with multiple demands are not acceptable excuses.
There are no excuses for failure to uphold academic integrity. To support your learning about academic
citation rules, please visit the Harvard Extension School Tips to Avoid Plagiarism (www.extension.
harvard.edu/resources-policies/resources/tips-avoid-plagiarism), where you’ll find links to
the Harvard Guide to Using Sources and two free online 15-minute tutorials to test your knowledge of
academic citation policy. The tutorials are anonymous open-learning tools.
Disability Accommodations:
The Extension School is committed to providing an accessible academic community. The Accessibil-
ity Office offers a variety of accommodations and services to students with documented disabilities.
More information can be found at www.extension.harvard.edu/resources-policies/resources/
accessibility-student-services
Dates of Interest:
◦ Harvard Extension School classes begin, January 25, 2021
◦ Pretest is due, January 29
◦ Last day to change the credit status, January 31
◦ Course drop deadline for full-tuition refund, January 31
◦ Quiz 1 is due, February 3
◦ Assignment 1 is due, February 7
◦ Course drop deadline for half-tuition refund, February 7
◦ Midterm Exam is due, March 17, 7:40 pm (Eastern Time)
◦ Withdrawal deadline, April 23
◦ Final Exam is due, May 12, 11:59 pm (Eastern Time)
3