6 commits

Author	SHA1	Message	Date
Martin Thoma	45e56d0320	Improve pseudocode	2016-08-02 16:08:01 +02:00
Martin Thoma	ea63ce4d57	Not learning rate but discount factor	2016-07-22 15:20:01 +02:00
Martin Thoma	001350bae4	Add q-learning and improve value iteration pseudocode	2016-07-14 15:20:45 +02:00
Martin Thoma	807b9268d0	Improve quality of description	2016-07-14 01:36:58 +02:00
Martin Thoma	940436c883	Update pseudocode to include cost function as parameter	2016-07-13 20:10:55 +02:00
Martin Thoma	d65f5d2933	Add pseudocode for policy- and value-iteration	2016-07-13 14:58:12 +02:00