AN2021 < AN < TWiki

Tags: view all tags

---+ 

---+ %MAKETEXT{"Autonomous Networking - A.A. 2021-2022 WILL START SEPT. 27th"}%

---++ Lecturer

<font size="+1"> [[http://reti.dsi.uniroma1.it/eng/maselli/][Gaia Maselli]] </font><br />Room 319<br />Dipartimento di Informatica<br />Via Salaria 113 - Roma <br />Tel. 06 4991 8438<br />Email: *maselli AT di.uniroma1.it*

---++ Class schedule
| *Day* | *Time* | *Place* |
| Tuesday | 1 pm - 3 pm | Alfa room, Via Salaria 113 |
| Friday | 8 am - 11 am | Alfa room, Via salaria 113 |
---++ Textbook and reading

   * Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto, Second Edition MIT Press, Cambridge, MA, 2018
   * Scientific papers (see course calendar)
---++ News

%RED%___ TODAY (FEB. 8TH) EXAM WILL START AT 9.30 ___%ENDCOLOR%

%RED%--- THE COURSE FOR A.Y. 2021-2022 WILL START SEPT 27TH ---%ENDCOLOR%

%BLACK%Exam of July 1rst will start at 10.00. Instructions for the exam will be sent tomorrow morning a few minutes before 10.00..%ENDCOLOR%

%BLACK%Please be ready to join Zoom meeting from the smartphone and GoogleMeet from the PC. Please check the following link for exam procedure:%ENDCOLOR%

[[https://docs.google.com/document/d/1FhEC_kUufW7Hk-S8VxAR5DhwoM5Tfyuj-KPvd3IRRbM/edit?usp=sharing]]

%BLACK%Results Feb EXAM [[%ATTACHURL%/Results-09-feb-2021.pdf][Results-09-feb-2021.pdf]] Send an email to Prof. Maselli to confirm and register your grade on Infostud.%ENDCOLOR%

INSTRUCTIONS FOR WRITTEN EXAM (FEBRUARY 9TH):

%BLACK%<u>FROM YOUR SMARTPHONE</u>:%ENDCOLOR%

%BLACK%Join Zoom Meeting USING SURNAME+MATRICOLA%ENDCOLOR%

%BLACK%https://uniroma1.zoom.us/j/99493030524?pwd=bGx5ZWZvZldVVTIxRzU4Rmp0emp6UT09%ENDCOLOR%

%BLACK%Meeting ID: 994 9303 0524%ENDCOLOR%

%BLACK%Passcode: NSh1Bi %ENDCOLOR%

%BLACK%<u>FROM YOUR PC</u>%ENDCOLOR%

%BLACK%Connect to <a href="https://twiki.di.uniroma1.it/twiki/edit/AN/GoogleMeet?topicparent=AN.WebHome;nowysiwyg=0" rel="nofollow" title="GoogleMeet (this topic does not yet exist; you can create it)">GoogleMeet</a> from your PC, possibly with institutional account (if you don’t have an institutional account use you personal one):%ENDCOLOR%

%BLACK%https://meet.google.com/bpa-idgb-ptp%ENDCOLOR%

%BLACK%Go on [[http://exam.net/][exam.net]] And log in (fill surname, matricola, etc.)%ENDCOLOR%

%BLACK%Key: ZDXjDV
%ENDCOLOR%

<p dir="ltr">%BLACK%Results January EXAM [[%ATTACHURL%/Results-Autonomous-Networking-Jan2021.pdf][Results-Autonomous-Networking-Jan2021.pdf]]%ENDCOLOR%</p> <p dir="ltr">%BLACK%HOMEWORK DISCUSSION JAN 22 AND JAN 29 ON ZOOM at 10.30%ENDCOLOR%</p>

%BLACK%If you are participating to the WRITTEN EXAM of Autonomous Networking scheduled for JANUARY 18 at 10.00, please <u>write your matricola number in the following google sheet</u> (I need to know how many students are participating to set up the Zoom conference)%ENDCOLOR%

[[https://docs.google.com/spreadsheets/d/1wK1lmqoaQivP4ReM_D_iuR2w1jGPNPZt02BYWQhnO54/edit?usp=sharing]]

Please also <u>read the instructions to participate to the exam</u> at the following link [[https://docs.google.com/document/d/1FhEC_kUufW7Hk-S8VxAR5DhwoM5Tfyuj-KPvd3IRRbM/edit?usp=sharing]]
<p dir="ltr"> </p> <p dir="ltr"> _IF YOU ARE ATTENDING THE COURSE: Please registers on Google Classroom site as soon as you have the university email account. Use code nkayl4e to register. Videos and notes of the course are available on the classroom site._ </p> <p dir="ltr"> _The course will start on *October 6*. Credentials to attend online are sent via email to the students registered at the following link._ </p> <p dir="ltr"> [[https://docs.google.com/spreadsheets/d/1o55RR7UNTuaSwIsxG9vsQrWF-R_wsYEKgZrmM01uFaI/edit?usp=sharing]]</p>
---++ Exam
   * Homeworks + oral discussion
   * written exam

---++ Calendar

<div title="Page 1">

Some images and slides in the following lectures are used from:

Fundamentals of Reinforcement Learning by University of Alberta & Alberta Machine Intelligence Institute
</div> <div title="Page 1">RL course by David Silver</div>

   * Oct. 6 - Course introduction: logistics, overview of covered topics. [[%ATTACHURL%/AutonomousNet-Class1.pdf][AutonomousNet-Class1.pdf]]
   * Oct. 9 - RFID systems: characteristics, issues, MAC protocols (tree based and aloha based) Slide: [[%ATTACHURL%/AutonomousNet-RFID-Class2-2021.pdf][AutonomousNet-RFID-Class2-2021.pdf]] Paper: [[%ATTACHURL%/TMC2011.pdf][TMC2011.pdf]]
   * Oct. 13 - Mobile Ad Hoc Networks. Wireless sensor newtorks: characteristics and applications. [[%ATTACHURL%/AutonomousNet-WSN-Class3-2021.pdf][AutonomousNet-WSN-Class3-2021.pdf]]
   * Oct. 16 - MAC protocols for wireless sensor networks (CSMA/CA, S-MAC) [[%ATTACHURL%/AutonomousNet-WSN2-Class4-2021.pdf][AutonomousNet-WSN2-Class4-2021.pdf]]
   * Oct. 20 - Canceled
   * --
   * Oct. 30 - Routing protocols for Ad Hoc and Sensor Networks [[%ATTACHURL%/AutonomousNet-WSN-Class5-2021.pdf][AutonomousNet-WSN-Class5-2021.pdf]] + Lab [[%ATTACHURL%/Autonomous_Networking_lab1_30_10_20.pdf][Autonomous_Networking_lab1_30_10_20.pdf]]
   * Nov. 3 - Internet of Things and battery free devices [[%ATTACHURL%/AutonomousNet-IoTBatteryFree-Class6-2021.pdf][AutonomousNet-IoTBatteryFree-Class6-2021.pdf]]
   * Nov. 6 - Drones and Dronets [[%ATTACHURL%/AutonomousNet-Dronet-Class7-2021.pdf][AutonomousNet-Dronet-Class7-2021.pdf]] + Lab [[%ATTACHURL%/DroNET_Simulator_LECTURE_2.pdf][DroNET_Simulator_LECTURE_2.pdf]]
   * Nov. 10 - Performance evaluation [[%ATTACHURL%/AutonomousNet-Performance-Class8-2021.pdf][AutonomousNet-Performance-Class8-2021.pdf]]
   * Nov. 13 - Canceled
   * Nov. 17 - Introduction to Reinforcement Learning [[%ATTACHURL%/AutonomousNet-RL1-Class9-2021.pdf][AutonomousNet-RL1-Class9-2021.pdf]]
   * Nov. 20 - Multi-armed bandits [[%ATTACHURL%/AutonomousNet-RL2-Class10-2021.pdf][AutonomousNet-RL2-Class10-2021.pdf]] + Lab (correction of previous exercise + homework assignment) [[%ATTACHURL%/DroNET_Simulator_lesson3.pdf][DroNET_Simulator_lesson3.pdf]]
   * Nov. 24 - Performance of action selection methods, UCB. [[%ATTACHURL%/AutonomousNet-RL3-Class11-2021.pdf][AutonomousNet-RL3-Class11-2021.pdf]]
   * Nov. 27 - Gradient Bandit, Regret, Contextual bandits [[%ATTACHURL%/AutonomousNet-RL4-Class12-2021.pdf][AutonomousNet-RL4-Class12-2021.pdf]] + Lab (question answering)
   * Dec. 01 - Markov Reward Processes, Markov Decision Processes [[%ATTACHURL%/AutonomousNet-RL5-Class13-2021.pdf][AutonomousNet-RL5-Class13-2021.pdf]]
   * Dec. 04 - Optimal policy, Q-learning [[%ATTACHURL%/AutonomousNet-RL6-Class14-2021.pdf][AutonomousNet-RL6-Class14-2021.pdf]] + Lab (solution to 1rst homework and assignment 2nd homework) [[%ATTACHURL%/AutNet_hmw2.pdf][AutNet_hmw2.pdf]]
   * Dec. 11 - Application of Q-learning to the Link Layer for adaptive radio selection [[%ATTACHURL%/AutonomousNet-RL7-Class15-2021.pdf][AutonomousNet-RL7-Class15-2021.pdf]] (paper [[%ATTACHURL%/AdaptiveLinkLayer.pdf][AdaptiveLinkLayer.pdf]]) + Lab (Question answering)
   * Dec. 15 - Application of Q-learning to the Aloha protocol in sensor networks [[%ATTACHURL%/AutonomousNet-RL8-Class16-2021.pdf][AutonomousNet-RL8-Class16-2021.pdf]]
   * Dec. 18 - Bayesian optimization [[%ATTACHURL%/DroNET_Simulator_18_12_2020.pdf][DroNET_Simulator_18_12_2020.pdf]] + Lab (question answering)
   * [[%ATTACHURL%/Results-Autonomous-Networking-Jan2021.pdf][ ]]

   * [[%ATTACHURL%/Results-09-feb-2021.pdf][Results-09-feb-2021.pdf]]: Results-09-feb-2021.pdf