Through a combination of classic papers and more recent work, students will explore automated decision-making from a computer-science perspective. They will examine efficient algorithms, where it exist, for single-agent and multi-agent planning as well as approaches to learning near-optimal decisions from experience.
Dozent: | Charles Isbell |
Bereitgestellt von: | Udacity |
Kurssprache: | Englisch |
Kosten: | kostenlos |
Level: | Fortgeschritten |
Zertifikat erhältlich? | (Gebühr) |
Format: | MOOC/Online-Kurs |
Wie gefällt Dir der Kurs 'Reinforcement Learning'?