Research map / Multi-agent systems and games / Games and equilibria
A Unified Diversity Measure for Multiagent Reinforcement Learning
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add UDM diversity term to PSRO (UDM-PSRO vs PSRO) | PSRO · Non-Transitive Mixture Model | PE(25) x10^2: -25.47 -> 1.81 | Helped |
| UDM-PSRO vs strongest diversity baseline RPD-PSRO | PSRO · Non-Transitive Mixture Model | PE(20) x10^2: 0.34 -> 0.69 | Helped |
| UDM-PSRO vs RPD-PSRO | PSRO · Non-Transitive Mixture Model | PE(25) x10^2: 1.39 -> 1.81 | Helped |
| UDM-PSRO vs RPD-PSRO | PSRO · Non-Transitive Mixture Model | PE(10) x10^2: 9.68 -> 9.73 | No clear effect |
| UDM-PSRO vs RPD-PSRO | PSRO · Non-Transitive Mixture Model | PE(15) x10^2: 0.39 -> 0.44 | No clear effect |
| UDM-PSRO vs plain PSRO | PSRO · Non-Transitive Mixture Model | exploitability x10^2: 33.71 -> 2.07 | Helped |
| UDM-PSRO vs RPD-PSRO | PSRO · Non-Transitive Mixture Model | exploitability x10^2: 1.95 -> 2.07 | No clear effect |
| UDM-PSRO vs EC-PSRO | PSRO · Non-Transitive Mixture Model | exploitability x10^2: 2.05 -> 2.07 | No clear effect |
| diversity-aware solvers vs those without diversity objective in AlphaStar meta-game | UDM-PSRO · AlphaStar meta-game | exploitability, PE, diversity | Helped |
| diversity-aware solvers on Blotto (3 areas, 10 coins) | UDM-PSRO · Blotto | exploitability, PE | No clear effect |
Closest papers by meaning
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.90)
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.89)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 2025 · similarity 0.87)
- Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners (NeurIPS 2024 · similarity 0.87)
- DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization (AAAI 2024 · similarity 0.87)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 2025 · similarity 0.86)
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.