Universal Decision Learners

Abstract:Many theories of decision making -- planning, reinforcement learning, causal intervention, online learning, and game-theoretic equilibrium -- turn local information into globally coherent behavior. This paper proposes a common categorical formulation: a Universal Decision Learner (UDL) extends a partially specified decision functor from observed contexts to new contexts by a pair of universal constructions. Left Kan extensions express rollout, aggregation, and candidate generation; right Kan extensions express consistency, constraint satisfaction, and fixed-point semantics. The central claim is not that every decision problem has the same algorithm, but that many decision formalisms instantiate the same universal problem: extend local behavioral data canonically, then characterize the globally coherent extensions. We give the abstract UDL construction, prove its universal comparison property, define Kan-invariant behavioral equivalence and minimal abstractions, and show how Bellman equations, planning recursions, causal interventions, online regret, and equilibria arise as special cases. The supplementary material develops the reinforcement-learning specialization in more detail.

Revised the central construction to use type-correct staged left/right Kan extensions; corrected the semantic quotient theorem; added an explicit discounted-MDP/Bellman derivation; and expanded the non-RL decision examples and limitations. A detailed change log appears in the supplement

Machine Learning (cs.LG)

arXiv:2605.30694 [cs.LG]

(or arXiv:2605.30694v2 [cs.LG] for this version)