atlas

Research map / Multi-agent systems and games / Games and equilibria

Depth-Limited Solving for Imperfect-Information Games

NeurIPS 2018 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 33 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
Replace naïve single-value depth limits with multi-valued state depth-limited solvingModicum · HUNL vs Baby Tartanian8mbb/g: -10 ± 8 -> 6 ± 5Helped
Replace naïve single-value depth limits with multi-valued state depth-limited solvingModicum · HUNL vs Slumbotmbb/g: -1 ± 15 -> 11 ± 9Helped
Replace rollout value estimates with DNN predictions (ablation)Modicum · HUNL vs Baby Tartanian8mbb/g: 6 ± 5 -> -11 ± 10Hurt
Offer multiple opponent strategies at the depth limit instead of only the blueprint strategy (ablation)Depth-limited solving in NLFH · NLFH off-tree 0.75× pot betexploitabilityHelped
Use only one state value at the depth limit (ablation)Depth-limited solving in NLFH · NLFH off-tree 0.75× pot betexploitabilityHurt

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