Sciweavers

AUTOMATICA
2008
107views more  AUTOMATICA 2008»
14 years 21 days ago
New algorithms of the Q-learning type
We propose two algorithms for Q-learning that use the two-timescale stochastic approximation methodology. The first of these updates Q-values of all feasible state
Shalabh Bhatnagar, K. Mohan Babu