AlphaZero: Learning Games from Selfplay

preview_player
Показать описание
Talk in the ZHAW Datalab Seminar series of lunch-time lectures, November 15, 2018.

Outline:
- Learning to act
- Example: DeepMind’s Alpha Zero
- Training the policy/value network

Issues:
- Sorry, no audio for the last 1.5 minutes of the Q&A part.

Рекомендации по теме
Комментарии
Автор

What I would really like to know, how an advanced agent is still able to react to dummy moves, if such dummy moves are not present in experience replay?

BorisBrodski
Автор

Holy crap the people in the audience are annoying. Asking a million questions that would be answered if they just wait...

generichuman_