Wsrtjtyk

up vote 0 down vote favorite I understand that epsilon marks the trade off between exploration and exploitation. At the beginning, you want epsilon to be high so that you take big leaps and learn things. As you learn about future rewards, epsilon should decay so that you can exploit the higher qvalues youve found. However, does our learning rate also decay with time in a stochastic environment? The posts on SO that I've seen only discuss epsilon decay. How do we set our epsilon and alpha such that values converge? machine-learning reinforcement-learning q-learning decay share | improve this question edited Nov 7 at 22:35

‹ The template Infobox recurring event is being considered for merging. › Sydney Film Festival Genre Film festival Date(s) June Frequency Annually Location(s) Sydney, New South Wales, Australia Years active 64 Inaugurated 1954 Website sff.org.au The Sydney Film Festival is an annual film festival held in Sydney, Australia, usually over 12 days in June. The competitive film festival draws international and local attention, with films being showcased in several venues across the city centre and includes features, documentaries, short films, retrospectives, films for families and animations. The festival's director is Nashen Moodley, who commenced in early 2012, [1] replacing Clare Stewart. [2] Contents 1 History 2 Festival format 3 Competition and film prizes 3.1 Winners of the Sydney Film Prize 4 Festival directors 5 Bibliography 6 References 7 External links History Influenced by the experi