Swap regret¶
The cumulative improvement available in hindsight from consistently replacing every occurrence of each chosen action with a possibly different alternative action.
Core Idea¶
Swap regret strengthens external regret by comparing realized play with every action-remapping function, and vanishing swap regret supports empirical distributions approaching correlated equilibrium. For each played action, counterfactual payoffs are accumulated for replacing that action by another; the best replacements are summed under the learner's realized action frequencies. The abstraction is therefore identified by a declared carrier, a transformation or constraint over that carrier, and an invariant that tells an analyst whether the named structure is genuinely present.
The load-bearing residual is not the broad topic of online learning and game theory. It is the domain-specific identity determined by the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements.
Scope of Application¶
Swap regret belongs to online learning and game theory and is useful where the analyst can specify the typed online learning and game theory carrier, defining objects and relations, parameters, conventions, evidence, boundary cases, and comparison targets, then evaluate the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements. The scope is broad within that domain but bounded by the need for the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements. The entry records a descriptive analytical identity; practical use requires the governing domain's evidence, standards, and safety obligations.
Clarity¶
The abstraction clarifies a crowded vocabulary by making the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements the center of the account. A claim should name the carrier, the governing operation or relation, the applicable assumptions, and the recognition test. A bare label is insufficient because the name Swap regret can be used for a formal identity, an implementation, or a neighboring result unless carrier and convention are stated.
Manages Complexity¶
Without the abstraction, an analyst must reason directly over many local details: the carrier roles, admissibility assumptions, competing conventions, derived invariants, boundary cases, and proof or validation obligations specific to Swap regret. Swap regret compresses them into the roles in the structural signature. That compression permits comparison across instances without erasing the variables that determine validity. It also exposes which details may be varied safely and which are constitutive.
Abstract Reasoning¶
- Identify the carrier. State what the elements, states, objects, or observations are: the typed online learning and game theory carrier, defining objects and relations, parameters, conventions, evidence, boundary cases, and comparison targets. Reject examples whose alleged carrier belongs to a different problem. 2. Lock the constitutive rule. Express the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements independently of one notation or implementation.
Knowledge Transfer¶
Knowledge transfers strongly among subfields of online learning and game theory because they reuse the typed online learning and game theory carrier, defining objects and relations, parameters, conventions, evidence, boundary cases, and comparison targets, For each played action, counterfactual payoffs are accumulated for replacing that action by another; the best replacements are summed under the learner's realized action frequencies., and type the carrier, state every parameter and convention in the definition, test that the action set, rounds, payoff feedback, randomization convention, and comparator class of action-by-action swaps are explicit and the regret aggregates the best conditional replacements, compare the nearest accepted identity, and report counterexamples, uncertainty, and limiting cases.
Relationships to Other Abstractions¶
Current abstraction Swap regret Domain-specific
Parents (1) — more general patterns this builds on
-
Swap regret is a kind of Counterfactual Reasoning Prime
The proposed strict upward parent is
prime:counterfactual_reasoning.
Hierarchy path (1) — routes to 1 parentless root
- Swap regret → Counterfactual Reasoning
Neighborhood in Abstraction Space¶
Swap regret sits in a moderately populated region (43rd percentile for distinctiveness): it has near-neighbors but no dense thicket of look-alikes.
Family — Equilibrium & Mechanism Design (13 abstractions)
Nearest neighbors
- Game form — 0.90
- Outcome (game theory) — 0.90
- Risk dominance — 0.89
- Quantal response equilibrium — 0.89
- Markov strategy — 0.89
Computed from structural-signature embeddings · 2026-09-08