Markov Decision Processes and the Basics of Temporal Difference Learning (pdf)
Markov Decision Processes and the Basics of Temporal Difference Learning
-
- 0 Rating
- 0 Reviews
- 0 Students Enrolled
Markov Decision Processes and the Basics of Temporal Difference Learning
Courselet on Reinforcement Learning, giving an entrance level description on problem formulation as Markov Decision Processes, the three curses of dimensionality and basic temporal difference methods.
-
- 0 Rating
- 0 Reviews
- 0 Students Enrolled
Courselet Content
2 components
|
|
2.82 M | |
|
Markov Decision Processes and the Basics of Temporal Difference Learning (video)
|
76 min |
Requirements
- Patricipants in this course are expected to have a basic understanding of stochastic models and (partially observable) Markov Decision Processes. Furthermore, a certain degree of familiarity with programming (the course will use Python), dynamic programming, calculus and statistics is expected.
General Overview
Description
Courselet on Reinforcement Learning, giving an entrance level description on problem formulation as Markov Decision Processes, the three curses of dimensionality and basic temporal difference methods. The courselet treats the following topics:
- Building blocks of Markov Decision Processes
- State-, action- and outcome spaces
- Post-decision states and look-up tables
- Introduction to temporal difference learning: Monte carlo learning, Q-learning and SARSA
Recommended for you
Meet the instructors !
About the Instructor
WP6 (Doctoral Training) coordinator and teacher in MSCA DIGITAL