Signals 4 · free daily AI digest

Constant regret in general games via higher-order optimism

Paper recorded by Signals 4 on 2026-09-03 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-03 on arXiv · recorded by Signals 4 on 2026-09-04

Category: cs.LG · 机器学习 · first seen 2026-09-04

Abstract

We introduce an uncoupled learning algorithm which, when employed by all players of an arbitrary $N$-player normal form game with up to $K$ actions per player, guarantees $O(N^3\log^2 K)$ individual regret, uniformly over the horizon of play. The proposed algorithm - which we call higher-order optimism with discounting (HOOD) is a variant of optimistic follow-the-regularized-leader (OptFTRL) that

Read on arXiv →

#131 most recent of 215 cs.LG papers we have recorded · ↑ newer: Prospective Coding Improves Learning in Deep Continuous-Time Recurrent · ↓ older: Hardware-Aware FP4 FlashAttention-4
Cite this page: Constant regret in general games via higher-order optimism: the #131 most recent of 215 cs.LG papers we have recorded (as of 2026-09-03). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/constant-regret-in-general-games-via-higher-order-optimism.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions