AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Safe Opponent-Exploitation Subgame Refinement

Mingyang Liu, Chengjie Wu, Qihan Liu, Yansen Jing, Jun Yang, Pingzhong Tang, Chongjie Zhang

NeurIPS 2022 · Learning theory and algorithms › Submodular and game algorithms · approach: Opponent modeling and subgame solving · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
use SES reach-distribution exploitation instead of EXP-STRATEGY fixed opponent strategy, alpha=0.7 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1exploitability: 134.37 -> 41.95Improved
use SES instead of EXP-STRATEGY, alpha=1.0 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1exploitability: 981.47 -> 55.10Improved
use SES instead of EXP-STRATEGY, alpha=0.3 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1exploitability: 34.75 -> 28.06Improved
use SES instead of EXP-STRATEGY, alpha=0.7 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1evaluation payoff: -27.22 -> 6.00Improved
use SES instead of EXP-STRATEGY, alpha=1.0 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1evaluation payoff: -88.94 -> 3.30Improved
use SES instead of EXP-STRATEGY, alpha=0.3 (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1evaluation payoff: 1.63 -> 6.21Improved
use SES instead of EXP-STRATEGY at alpha=0.0 (pure safety) (ablation)SES · FHP, Pr_shuffle=0.3, estimation error 0.1exploitability and evaluation: 29.43 -> 29.43No clear effect
increase exploitation level alpha from 0.0 to 1.0 in SESSES · FHP, Pr_shuffle=0.3, estimation error 0.1exploitability: 29.43 -> 55.10Hurt
increase exploitation level alpha from 0.0 to 0.3 in SESSES · FHP, Pr_shuffle=0.3, estimation error 0.1evaluation payoff: 5.15 -> 6.21Improved
increase alpha from 0.3 to 1.0 in SES under estimation error 0.1SES · FHP, Pr_shuffle=0.3, estimation error 0.1evaluation payoff: 6.21 -> 3.30Hurt
increase estimation error epsilon of opponent model (0.0 to 1.2)SES · Leduc and FHP, Pr_shuffle 0.0/0.3/0.7exploitability and payoffHurt
increase alpha with accurate opponent estimate (epsilon=0.0)SES · FHP head-to-headexpected payoffImproved

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