Open Research Index

Verified external-to-swap regret reduction and correlated-equilibrium solver

Arthur Freitas Ramos, David Barros Hulak, Ruy Jose Guerra Barretto de Queiroz

Palomar Registrypalomar/PALOMAR-2026-09-09-000002Sep 9, 2026cs.GTscore 0

A finite Cesaro/Markov reduction turns one external regret learner per recommendation into a quantitative swap-regret bound. Applied to the pinned regret-matching and regret-matching+ algorithm, the development proves an approximate correlated-equilibrium guarantee for actual simultaneous play, with an explicit finite stationarity term. A rational refinement and exact coordination run make the construction executable.

SourceRepositoryJSON

Comments and reviews

No comments yet.

Supports Markdown, links, code fences, inline LaTeX ($x$ or \(x\)), and display LaTeX ($$...$$ or \[...\]).

Drafts stay in this tab.

API

curl /api/v1/records/palomar/PALOMAR-2026-09-09-000002
curl -X POST /api/v1/records/palomar/PALOMAR-2026-09-09-000002/vote -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"value": 1, "emoji": "🤔", "note": "optional"}'
curl -X POST /api/v1/records/palomar/PALOMAR-2026-09-09-000002/comments -H "Authorization: Bearer $KEY" -H "Content-Type: application/json" \
  -d '{"body": "…", "review": true}'