AI Paper Atlas

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

Evolving Action Abstractions for Real-Time Planning in Extensive-Form Games

Julian R. H. Mariño, Rubens O. Moraes, Claudio Toledo, Levi H. S. Lelis

AAAI 2019 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas · 20 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 evolved action abstraction (PGS*) instead of rush abstraction PGSrPGS · uRTS 24x24 direct matchwin rate (%): PGSr wins 0.4% of matches vs PGS*Improved
use evolved abstraction (SSS*) instead of SCV-strategy abstraction SSSsSSS · uRTS 24x24 direct matchwin rate (%): SSS* wins 93.2% vs SSSsImproved
use evolved abstractions vs hand-crafted abstraction for win rate against WRPGS/SSS · uRTS 24x24 vs WRwin rate (%): 90.3 -> 78.8 (PGSs vs PGS*)Hurt
evolved abstraction vs STT (2017 competition winner)PGS/SSS · uRTS 24x24win rate (%): 99.8 (PGS*), 98.6 (SSS*)Improved
evolved abstraction vs STTPGS/SSS · uRTS 64x64win rate (%): 95.2 (PGS*), 91.0 (SSS*)Improved
evolved abstraction vs SCVPGS/SSS · uRTS 32x32win rate (%): 86.5 (PGS*), 91.5 (SSS*)Improved
evolved abstraction vs PSPGS/SSS · uRTS 64x64win rate (%): 83.8 (PGS*), 77.5 (SSS*)Improved
use PGS* instead of SSS* as search algorithmPGS/SSS · uRTS 64x64 head to headwin rate (%): SSS* wins 62.8% vs PGS*No clear effect
evolve subset from 300 generated strategies instead of 8 hand-designed (win vs baselines grows with map size)PGS/SSS · uRTS mapswin rate (%): 24x24 to 64x64Improved
evolutionary subset selection converges to WR-dominated population (ablation)evolutionary algorithm · uRTS 8x8, |Z|=8,10,15WR fraction in populationImproved

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