Swap regret

Swap regret is a concept from online learning and game theory.

Uses your system voice; voice and rate in settings.

Snapshot

≈ 1 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

Swap regret is a concept from online learning and game theory. It is a generalization of regret in a repeated, n-decision game.

Definition

In each round t , the learner chooses decision i with probability x^t_i and the utility for decision i is p^t_i . A learner's swap-regret is defined to be the following: \mbox{swap-regret}= \sum_{i=1}^n \max_{j \leq n}\sum_{t=1}^T x^t_i \cdot (p^t_j-p^t_i). Intuitively, it is how much a player could improve by switching each occurrence of decision i to the best decision j possible in hindsight. The swap regret is always nonnegative.

Swap regret is useful for computing correlated equilibria.

References

.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1305880026 under CC BY-SA 4.0; modifications have been made.

Sources cited in this revision

No external citation was extracted for this revision. That is a statement about the source, not a claim that none exists.