After successful completion of the course, students are able to not only understand, to explain and to apply the theory and the methods of reinforcement learning including the latest developments, but also to implement the most important algorithms.
Reinforcement learning is a field of artificial intelligence and is concerned with the development of strategies that an agent uses to maximize its reward in a random environment in a model-free manner.
Applications include robotics (OpenAI gym), computer vision, games (such as Go, chess, Atari 2600, or Dota 2) at the human level or above and many more.
Theory and algorithms of reinforcement learning:
- Introduction
- Bandit problems
- Markov decision problems
- Bellman equations
- Hamilton-Jacobi-Bellman equation
- Dynamic programming
- Monte-Carlo learning
- Temporal-difference learning
- Tabular methods
- Function approximation and deep learning
- On-policy vs. off-policy
- Eligibility traces
- Policy gradients and actor-critic
- Applications
In the tutorial, the theory will be repeated and extended and the algorithms will be implemented.
Vorbesprechung: Do., 4.3., um 15:00 via GoToMeeting.
==========
VU Reinforcement Learning
Nehmen Sie an meinem Meeting per Computer, Tablet oder Smartphone teil.
https://global.gotomeeting.com/join/206032389
Sie können sich auch über ein Telefon einwählen.
Österreich: +43 7 2081 5337
Zugangscode: 206-032-389
Nehmen Sie über einen Videokonferenzraum oder ein Videokonferenzsystem teil.
Einwählen oder Eingabe: 67.217.95.2 oder inroomlink.goto.com
Meeting-ID: 206 032 389
Oder Direktwahl: 206032389@67.217.95.2 oder 67.217.95.2##206032389
Sie kennen GoToMeeting noch nicht? Installieren Sie jetzt die App, damit Sie für Ihr erstes Meeting bereit sind:
https://global.gotomeeting.com/install/206032389
==========