AI Paper Atlas

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

Chaos, Extremism and Optimism: Volume Analysis of Learning in Games

Yun Kuen Cheung, Georgios Piliouras

NeurIPS 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Zero-sum game learning dynamics · 21 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 MWU in a zero-sum game rather than OMWUMWU and OMWU · Zero-sum gamesdual-space volume change: MWU expands volume; OMWU contracts volumeMixed
Use OMWU in a coordination game rather than MWUMWU and OMWU · Coordination gamesdual-space volume change: OMWU expands volume; MWU contracts volumeMixed
Apply OMWU to zero-sum gamesOMWU · Zero-sum gamesdual-space volume change: volume contracts exponentiallyImproved
Apply OMWU to non-trivial coordination gamesOMWU · Coordination gamesdual-space volume change: (1 + ε²δ²(α₁)²/4)^THurt
Use MWU in zero-sum gamesMWU · Zero-sum gamesavoidance of bad statesHurt
Use MWU in zero-sum games satisfying the theorem conditionsMWU · Zero-sum gamesreaching extremal domain: threshold δHurt
Use MWU in Rock-Paper-ScissorsMWU · Rock-Paper-Scissorsextremism periods: 22 periods within 30000 time steps; each period has length around 350Hurt

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