Open meandor opened 5 years ago
As an agent I want to be able to use Q-Learning to use as a strategy so that I can play snake
Given I am starting to play a game of snake When I do not add any parameters to the learning algorithm Then default values are used (epsilon-greedy)
Tech notes: https://en.wikipedia.org/wiki/Q-learning
algorithm: https://martin-thoma.com/images/2016/07/q-learning.png
https://www.youtube.com/watch?v=6SDCwn8MGtQ
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html
As an agent I want to be able to use Q-Learning to use as a strategy so that I can play snake
Acceptance Criteria
AC1
Given I am starting to play a game of snake When I do not add any parameters to the learning algorithm Then default values are used (epsilon-greedy)
Tech notes: https://en.wikipedia.org/wiki/Q-learning
algorithm: https://martin-thoma.com/images/2016/07/q-learning.png
https://www.youtube.com/watch?v=6SDCwn8MGtQ