MIStatlE
中文

← Knowledge map∇ Algorithms & Optimization

Reinforcement Learning

3 concepts, 1 written; shares concepts or relations with 5 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.

12 earlierlater ∇Reinforcement Learning KL Divergence &Cross Entropy MDPs & ValueFunctions Policy Gradient Shannon Entropy → KL Divergence & Cross Entropy · extends to — KL divergence is relative entropy: entropy extended from one distribution to a pair.Information Theory · Shannon E… → KL Divergence & Cross Entropy → VAE & ELBO · applied in — The regularizer in the ELBO is a KL divergence.→ Generative Models · VAE & ELBO Stochastic Gradient Methods → Policy Gradient · applied in — The update is stochastic gradient ascent on J(θ); its convergence analysis is that of stochastic nonconvex optimization.Optimization · Stochastic Gra… →
Relationsposition is order: read along the rail, left to righta tag on a card leads to another subject
NodesConceptMethodwrittenplanned1 / 3 written

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

Reinforcement Learning1/3

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

Relations in this subject, in words4

  • Shannon Entropyextends toKL Divergence & Cross Entropy

    KL divergence is relative entropy: entropy extended from one distribution to a pair.

  • KL Divergence & Cross Entropyapplied inVAE & ELBO

    The regularizer in the ELBO is a KL divergence.

  • 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.

Notes

Notes in this subject

Filter the notes page by this subject →
Reinforcement LearningMechanism Policy Gradient from an Optimization Viewpoint One continuous line from the objective to gradient estimation, variance and stepsize choice. Read →