Observer / CONCEPT
Stationary Policy Optimality
Bellman-greedy stationary policies have the optimal discounted value, with sharp global-state and discount hypotheses.
Closed
DIRECT PREREQUISITES1
DIRECT CONSEQUENCES1
PROOF DEPTH1
DOCUMENT LINKS1
The loss Bellman operator is a finite minimum
RELATIONSHIP ATLAS
Every connection, in context.
Direct recorded relationships
Proof dependencyStructural affinityDocument link
Certified topology / UPSTREAM
Prerequisites
Certified topology / DOWNSTREAM
Consequences
RELATED KNOWLEDGE
Structural connections
- Actual-Posterior Information Gain Can Increasestructural-affinity · Closed
- Adaptive Posterior-Policy Sufficiencystructural-affinity · Closed
- Discounted Bellman Contraction and Fixed Valuestructural-affinity · Closed
- Epsilon Stopping and Pair-Evidence Completionstructural-affinity · Closed
- Fifth-Stage Evidence, Belief, and Decision Theorem Mapstructural-affinity · Closed
- Posterior Stopping MAP Error Boundstructural-affinity · Closed
- Three-State Adaptive Early Stoppingstructural-affinity · Closed
- Universal Sufficiency of the Posteriorstructural-affinity · Closed
Documents & exposition
Other authored & advisory relationships
None recorded in this release.
LIBRARY / RELEASE VERSIONS
Content history
Loading release versions...
Browse the archiveCertified provenance