What Must Be Learned to Adapt? Decision-Directed Identification Under Environment Shift

Pretraining is useful only when the knowledge it supplies rules out alternatives that would change the downstream decision. Yet adaptation is commonly described by overall source–target distance or by how much uncertainty pretraining removes, quantities that can be dominated by variation irrelevant to acting well. We formulate post-shift adaptation as $decision\text{-}directedidentification$: after observing a source artifact, an agent should distinguish only target hypotheses that require incompatible decisions. This formulation yields a residual information radius and an instance-wise lower bound on target interaction. We operationalize the principle with Decision-Directed Adaptation (DDA), which probes decision-conflicting alternatives and stops once all plausible targets share an $ϵ$-good decision. Controlled experiments show that DDA can require substantially fewer probes than random exploration, full system identification, and decision-agnostic information gain. They also show that environmental distance can reverse the true ordering of adaptation difficulty and that retaining abundant nuisance information may provide little decision value. Robot experiments across seven Panda-to-XArm PickCube shifts and more than 200,000 held-out episodes expose the same practical structure: zero-shot transfer ranges from sufficient to ineffective, scratch learning and fine-tuning exchange advantage across shifts, and action history resolves an important latency-induced information deficiency. The resulting perspective turns transfer from a vague similarity judgment into a concrete question: which decision conflicts remain, and what evidence is needed to eliminate them?