[ 536MLPEREIU20 ] UE Reinforcement Learning

Workload Education level Study areas Responsible person Hours per week Coordinating university
1,5 ECTS B3 - Bachelor's programme 3. year (*)Artificial Intelligence Gerhard Widmer 1 hpw Johannes Kepler University Linz
Detailed information
Original study plan Bachelor's programme Artificial Intelligence 2020W
Objectives Consolidation of content taught in the lecture through practical implementation
  • Implementing and testing selected solution methods for k-armed Bandits
  • Implementing and testing selected table-based solution methods for MDPs with discrete state spaces
  • Implementing and testing selected approximate solution methods for MDPs with continuous state spaces
Criteria for evaluation
  • Active participation
  • Positive completion of exercises
  • Thorough explanation of the used software
  • Verbal explanation of each new exercise, additional hints, programming tips, and practical examples
Language English
Study material Richard S. Sutton and Andrew G. Barto. 2018. Introduction to Reinforcement Learning (2nd. edition). MIT Press, Cambridge, MA, USA.
Changing subject? No
Corresponding lecture in collaboration with 536MLPEREIV20: VL Reinforcement Learning (3 ECTS) equivalent to
536MLPEREIK19: KV Reinforcement Learning (4.5 ECTS)
On-site course
Maximum number of participants 24
Assignment procedure Direct assignment