AI Paper Atlas

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

Modelling Behavioural Diversity for Learning in Open-Ended Games

ICML 2021 · Learning theory and algorithms › Submodular and game algorithms · approach: Opponent modeling and subgame solving · 13 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
Add the DPP expected-cardinality diversity objective to PSROPSRO on the 28 real-world meta-games · 28 real-world meta-gamesexploitabilityMixed
Add the DPP expected-cardinality diversity objective to PSROPSRO on the 28 real-world meta-games · 28 real-world meta-gamesdiversityHelped
Add the DPP expected-cardinality diversity objective to PSROPSRO on the non-transitive mixture model · Non-Transitive Mixture ModelexploitabilityHelped
Add the DPP expected-cardinality diversity objective to PSROPSRO in Colonel Blotto · Colonel Blotto, 3 areas and 10 coinsexploitabilityHelped
Add a DPP-based diversity-aware oracle to α-PSROα-PSRO on randomly generated zero-sum normal-form games · Randomly generated zero-sum normal-form gamesPCS-scoreHelped

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