Research map / Multi-agent systems and games / Games and equilibria
Similarity-based cooperative equilibrium
Caspar Oesterheld, Johannes Treutlein, Roger Baker Grosse, Vincent Conitzer, Jakob Nicolaus Foerster
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add CCDR pretraining before alternating best response training (ablation) | ABR learning in the diff meta game · HDPD (G=5) | average utility: -5.257 -> -2.77 | Improved |
| add CCDR pretraining before alternating best response training (ablation) | ABR learning in the diff meta game · HDPD (G=5) | runs reaching cooperative equilibrium: 26 out of 28 | Improved |
| remove CCDR pretraining (random init, ABR only) (ablation) | ABR learning · HDPD (G=5) | cooperation (min-player utility): -5.257 | Hurt |
| continue ABR training after CCDR pretraining | CCDR-pretrained policies · HDPD (G=5) | degree of cooperation | Hurt |
| use LOLA opponent shaping instead of CCDR pretraining | learning similarity-based cooperation · HDPD (G=5) | robustness of learning cooperation | Mixed |
| CCDR pretraining in symmetric additively decomposable game | ABR after CCDR · HDPD (G=5) | utility gap between players: 0.04 | Improved |
| vary hyperparameters / setup of CCDR (exploratory) | CCDR · HDPD (G=5) | success of cooperation | Mixed |
Closest papers by meaning
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · similarity 0.87)
- Aligning Individual and Collective Objectives in Multi-Agent Cooperation (NeurIPS 2024 · similarity 0.86)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.86)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · similarity 0.85)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.85)
- Approximating the Shapley Value without Marginal Contributions (AAAI 2024 · similarity 0.85)
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.
