Login / Signup

A stochastic approximation method with max-norm projections and its applications to the Q-learning algorithm.

Sumit KunnumkalHuseyin Topaloglu
Published in: ACM Trans. Model. Comput. Simul. (2010)
Keyphrases
  • learning algorithm
  • dynamic programming
  • objective function
  • neural network
  • machine learning
  • support vector machine
  • image sequences
  • computational complexity
  • pairwise
  • optical flow
  • cost function