← Knowledge map∇ Algorithms & Optimization

Optimization

3 concepts, 1 written; shares concepts or relations with 2 other subjects. Earlier ideas sit to the left, a region holds one chapter, and relations that leave the subject hang on the cards as tags.

Relationsposition is order: read along the rail, left to right

NodesConceptMethodwrittenplanned1 / 3 written

Select a concept to see its summary and relations1 / 3 written

Optimization1/3

Select a node to see its summary and how it relates to the others.

Relations in this subject, in words2

MDPs & Value FunctionsrequiresPolicy Gradient
The objective J(θ) is defined over the MDP's trajectory distribution.
Stochastic Gradient Methodsapplied inPolicy Gradient
The update is stochastic gradient ascent on J(θ); its convergence analysis is that of stochastic nonconvex optimization.