expand_less
Responsible: Ben Goertzel
Papers: Hyperon for AGI⇒ASI Whitepaper (2025), §5.9
Status: Proposed. Framework for certified subgoal management described in the 2025 whitepaper.TheTheoretical CDS/PDSdesign; admissionnot rulesyet andimplemented. Motive Decomposition Network are theoretical designs.
SubRep (Subgoal Representation) proposes transforming subgoal and option learning into a disciplined, certifiablepracticepractice. withIts core mechanisms are formal mathematicaladmission certificatesrules designedand toa guaranteeco-learned decomposition network that together determine when a subgoal genuinely serves a larger purpose and when component solutions can be safely composed.
The Problem
Standard reinforcement learning discovers subgoals by shaping a single scalar reward. This approach is brittle: skills overfit to specific reward signals, transfer negatively to related tasks, and cannot be reliably composed. PRIMUS needs subgoals that work across multiple motives, compose safely, and serve both neural controllers and symbolic reasoners.
ProposedCore Certificate-DrivenMechanisms Admission
SubRepSubRep's introducesdesign twocenters formalon admissionfour rules:elements described in the whitepaper and supporting glossary:
CDS (Cone-Dominant Subgoals): An option is admitted if robust across a family ofmotives,motives preventing— not just optimal for one reward, but beneficial across a "cone" of related objectives in motive space. This prevents brittle specialization.
PDS (Pareto-Dominant Subgoals): When genuine trade-offsexist,exist between motives, an option is admitted if Pareto-good on a small covering set.set — meaning no other available option dominates it on all objectives simultaneously.
These certificates(Motive wouldDecomposition beNetwork): A co-learned network that decomposes high-level motives into achievable subgoals, mapping motive space into option space. The MDN learns which skills serve which purposes and identifies gaps.
Weakest-sufficient decomposition: SubRep uses residuation from the weakness framework to find decompositions that are sufficient for the task but no stronger than necessary — preventing over-specialized subgoals that fail to transfer.
Certificates are expressed as backed-up values over AtomSpacefeatures.features, making them native to the broader neurosymbolic loop.
Neurosymbolic Design
Unlike standard RL option frameworks, SubRep is designed to work equally for neural controllers, PLN-derived logic macros, and MOSES/GEO-EVO evolved programs — all screened by the same CDS/PDS admissionrules.rules and composed by the same planner.
Relationship to MetaMo and TransWeave
SubRep is designed as a complement to MetaMo: MetaMo defines what the system cares about; as motive geometries; SubRep validates which skills serve those motives. with formal certificates. When TransWeave transfers skills, SubRep certificates would travel with them.
Key References
Goertzel, B. (2025). Hyperon for AGI⇒ASI Whitepaper, §5.9: SubRep
Papers: Hyperon for AGI⇒ASI Whitepaper (2025), §5.9
Status: Proposed. Framework for certified subgoal management described in the 2025 whitepaper.
SubRep (Subgoal Representation) proposes transforming subgoal and option learning into a disciplined, certifiable
The Problem
Standard reinforcement learning discovers subgoals by shaping a single scalar reward. This approach is brittle: skills overfit to specific reward signals, transfer negatively to related tasks, and cannot be reliably composed. PRIMUS needs subgoals that work across multiple motives, compose safely, and serve both neural controllers and symbolic reasoners.
CDS (Cone-Dominant Subgoals): An option is admitted if robust across a family of
PDS (Pareto-Dominant Subgoals): When genuine trade-offs
Weakest-sufficient decomposition: SubRep uses residuation from the weakness framework to find decompositions that are sufficient for the task but no stronger than necessary — preventing over-specialized subgoals that fail to transfer.
Certificates are expressed as backed-up values over AtomSpace
Neurosymbolic Design
Unlike standard RL option frameworks, SubRep is designed to work equally for neural controllers, PLN-derived logic macros, and MOSES/GEO-EVO evolved programs — all screened by the same CDS/PDS admission
Relationship to MetaMo and TransWeave
SubRep is designed as a complement to MetaMo: MetaMo defines what the system cares about
Key References
Goertzel, B. (2025). Hyperon for AGI⇒ASI Whitepaper, §5.9: SubRep