TD(0) - Optimal Control

Learn online the Q function.

Qt+1 (st ,at ) = Qt (st ,at )+ a [ rt+g Qt (st+1,at+1) - Qt (st ,at )]

at+1 the e-greedy policy for Qt.

CONVERGENCE: GUARANTEED [S,JJS]

sarsa - algorithm

Previous slide

Next slide

Back to first slide

View graphic version