Loading...
Uploaded by MichaelKaisers on Apr 27, 2010
This video illustrates the learning behavior of different variations of two algorithms (FALA and Q-learning) in three games: Prisoners' Dilemma (FALA, Q-learning), Matching Pennies (FALA, Lenient Q-learning), Battle of the Sexes (FALA, Q-learning).
Science & Technology
Standard YouTube License
Awesome. How were the visuals created?
rhaikh 1 year ago
@rhaikh Simulations were performed in Matlab.
MichaelKaisers 1 year ago
can you post the code please..
bpkumar87 6 months ago
Load more suggestions
Awesome. How were the visuals created?
rhaikh 1 year ago
@rhaikh Simulations were performed in Matlab.
MichaelKaisers 1 year ago