AI RESEARCH
Universal Decision Learners
arXiv CS.LG
•
ArXi:2605.30694v1 Announce Type: new 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.