Research map / Learning theory and algorithms / Submodular and game algorithms
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games
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 |
|---|---|---|---|
| Use a hierarchical pipeline of parallel workers, fixing a policy when it plateaus | PSRO · Random symmetric normal-form games | exploitability | Helped |
| Use a hierarchical pipeline of parallel workers, fixing a policy when it plateaus | PSRO · Leduc poker | exploitability: 0.4 exploitability almost twice as soon as Naive PSRO | Helped |
| Use a hierarchical pipeline of parallel workers, fixing a policy when it plateaus | PSRO · Barrage Stratego vs. existing bots | win rate: 71% on average after 820,000 episodes; over 65% against each bot | Helped |
| Use DCH with an annealed learning rate instead of a constant learning rate | DCH · Random symmetric normal-form games | exploitability | Helped |
| Use DCH with an annealed learning rate | DCH · Random symmetric normal-form games | convergence speed | Mixed |
| Use Rectified PSRO, which restricts training opponents to policies the learner beats | PSRO · Random symmetric normal-form games | convergence to approximate Nash equilibrium | Hurt |
| Use DCH, allowing early-level policies to continue changing | PSRO · Random symmetric normal-form games | convergence to approximate Nash equilibrium | Hurt |
Closest papers by meaning
- A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games (ICML 2025 · similarity 0.90)
- Explicit Exploration for High-Welfare Equilibria in Game-Theoretic Multiagent Reinforcement Learning (ICML 2025 · similarity 0.88)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.87)
- Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning (AAAI 2024 · similarity 0.87)
- Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning (ICLR 2025 · similarity 0.87)
- Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning (ICLR 2024 · 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.