atlas

Research map / Bandits and online learning / Online convex optimization and games

Strategy-Based Warm Starting for Regret Minimization in Games

AAAI 2016 · Bandits and online learning › Online convex optimization and games · approach: Counterfactual regret minimization · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
warm start CFR (regrets reset from the average strategy) after 100, 500 or 2500 iterations instead of continuing plain CFRCFR · Flop Texas Hold'emexploitability vs iterations: warm started to 97, 490 and 2310 iterationsNo clear effect
warm start every iteration from the average strategy, storing no regretsCFR · random 100x100 normal-form gamesconvergenceNo clear effect
warm start full-game CFR with an abstract-game MCCFR strategyCFR · Flop Texas Hold'emexploitability over time: warm started to T = 70 using lambda = 0.08Helped
set only the starting strategy without initializing regrets (naive warm start)regret matching · 2x2 normal-form exampleregret: second-iteration regret 1.9933 for Player 1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy