Politecnico di Milano
Manifesti degli Studi
 
Menu
Degree programme
Programme Structure
Show/Search Programme
Course Details
Save Document
Degree Programme
Degree Programme not available
Faculty
Infrastructures
Quantitative data
International context
Customized Schedule
Your customized time schedule has been disabled
Enable
Your customized schedule contains 0/15 courses
Delete schedule
Search
Search a Professor
Search a Course
Search a Course (system prior D.M. n. 509)
Search Lessons taught in English
Exit

Glossary
Semester (Sem)
1First Semester
2Second Semester
AAnnual course
Educational activities
BIdentifying activities
Language
Course completely offered in italian
Course completely offered in english
--Not available
Innovative teaching
The credits shown next to this symbol indicate the part of the course CFUs provided with Innovative teaching.
These CFUs include:
  • Subject taught jointly with companies or organizations
  • Blended Learning & Flipped Classroom
  • Massive Open Online Courses (MOOC)
  • Soft Skills
Degree ProgrammesCambia LinguaCambia Lingua
Course Details

Context
Academic Year 2014/2015
School School of Industrial and Information Engineering
Name (Master of Science degree)(ord. 270) - MI (434) Engineering of Computing Systems
Track T2A - Sistemi e applicazioni dell'Informatica
Programme Year 2

Course Details
ID Code 093549
Course Title REINFORCEMENT LEARNING
Course Type Mono-Disciplinary Course
Credits (CFU / ECTS) 5.0
Semester --
Course Description Reinforcement learning deals with solving sequential decision making problems, when no (or minimal) prior information is available. Solving sequential decision making problems means to find their optimal control policies. Using reinforcement-learning algorithms, the optimal policy is learned through the direct interaction between the agent (or controller) and the system to be controlled. The course will introduce the main modeling frameworks, will analyze the most relevant reinforcement-learning techniques, and, finally, some interesting applications of these techniques to real-world domains will be shown. 1) Models * Finite Markov Decision Processes * Continuous Markov Decision Processes * Partially Observable Markov Decision Processes * Semi Markov Decision Processes * Markov Games 2) Algorithms * Value Iteration based algorithms (Q-learning, SARSA, TD(lambda)) * Policy Iteration based algorithms (actor-critic methods, LSPI) * Policy Search algorithms (policy gradient methods and stochastic search techniques) * Exploration techniques (R-MAX, model-based Interval Estimation) * Model-free vs Model-based algorithms * Batch algorithms (Fitted Q-iteration) * Function approximation in Reinforcement Learning algorithms * Hierarchical Learning (options, HAMs, MAX-Q) * Multi-Agent Learning techniques (basic elements) 3) Applications * Autonomic Computing * Robot Control * Water Resources Management
Scientific-Disciplinary Sector (SSD)
Educational activities SSD Code SSD Description CFU
B
ING-INF/05
INFORMATION PROCESSING SYSTEMS
5.0

Schedule, add and removeAlphabetical groupProfessorLanguageCourse details
From (included)To (excluded)
--AZZZZRestelli Marcello
18/04/2019 Area Servizi ICT v. 2.11.10 / 2.11.10