Research map / Learning theory and algorithms / Submodular and game algorithms
Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Runtime analysis of competitive coevolutionary algorithms on impartial combinatorial games, showing that diverse and challenging opponents speed up coevolution.
Problem
Competitive coevolutionary algorithms (CoEAs) lack theoretical understanding of how to avoid pathological behaviour, such as cycling or stalled progress, in adversarial settings.
Approach
Uses impartial combinatorial games as a challenging domain and provides a runtime analysis of CoEAs, examining how individuals' interactions with diverse and challenging opponents drive coevolutionary progress.
Experimental setup
Metrics: expected runtime
Closest papers by meaning
- Towards Runtime Analysis of Population-Based Co-evolutionary Algorithms on Sparse Binary Zero-Sum Game (AAAI 2025 · similarity 0.90)
- Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games (AAAI 2021 · similarity 0.87)
- Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results (ICML 2021 · similarity 0.86)
- Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games (ICML 2024 · similarity 0.85)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.85)
- Opponent Modeling based on Subgoal Inference (NeurIPS 2024 · similarity 0.84)
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.