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. The CDS/PDS admission rules and Motive Decomposition Network are theoretical designs.

SubRep (Subgoal Representation) proposes transforming subgoal and option learning from an ad-hoc process into a disciplined, certifiable practice.practice Itwith provides formal mathematical certificates designed to guarantee when a subgoal genuinely serves a larger purpose and when component solutions can be safely composed.

Status: Proposed. SubRep is described in the 2025 whitepaper (§5.9) as a framework for certified subgoal management within PRIMUS. The CDS/PDS admission rules and Motive Decomposition Network are theoretical designs; implementation is a research goal.

The Problem

Standard reinforcement learning discovers subgoals by shaping a single scalar rewardreward. and hoping the resulting skills transfer to new contexts. This approach is brittle: skills overfit to specific reward signals, transfer negatively to related tasks, and cannot be reliably composedcomposed. into larger plans. PRIMUS needs subgoals that work across multiple motives, compose safely, and serve both neural controllers and symbolic reasoners.

Proposed Certificate-Driven Admission

SubRep introduces two formal admission rulesrules: that would screen candidate options (subgoal-reaching policies) before they enter the system's skill library:


CDS (Cone-Dominant Subgoals): An option is admitted if robust across a family of motivesmotives, —preventing not just optimal for one reward, but beneficial across a "cone" of related objectives. This prevents brittle specialization.
PDS (Pareto-Dominant Subgoals): When genuine trade-offs existexist, between motives, an option is admitted if explicitly Pareto-good on a small covering setset. — meaning no other available option dominates it on all objectives simultaneously.


These certificates would be expressed inas the same language the rest of Hyperon speaks — backed-up values over AtomSpace featuresfeatures. — so they could benefit from and contribute to the broader neurosymbolic loop.

Motive Decomposition Network

SubRep proposes co-learning a Motive Decomposition Network (MDN) that decomposes high-level motives into achievable subgoals, learning the geometry of how motives relate to each other and to available skills.

Neurosymbolic Design

Unlike standard RL option frameworks, SubRep is designed to work equally for:for

Neural controllersneural (learnedcontrollers, policies)PLN-derived
Logic macroslogic (PLN-derivedmacros, inferenceand strategies)MOSES/GEO-EVO
Evolved evolved programs (MOSES/GEO-EVO— outputs)all


All would be screened by the same CDS/PDS admission rulesrules. and composed by the same planner, making SubRep a universal interface between PRIMUS's diverse skill generators and its planning system.

Relationship to MetaMo and TransWeave

SubRep is designed as a complement to MetaMoMetaMo: (motivational framework): MetaMo defines what the system cares about; as motive geometries; SubRep validates which skills actually serve those motives. with formal certificates. When TransWeave transfers skillsskills, to new domains, SubRep certificates would travel with them.

Key References

Goertzel, B. (2025). Hyperon for AGI⇒ASI Whitepaper, §5.9: SubRep