Research map / Multi-agent systems and games / Cooperative multi-agent RL
Decentralized Mean Field 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 decentralized mean-field Q-learning with an estimated current mean field rather than a previous global mean field | Mean-field reinforcement learning · Battle | cumulative reward | Helped |
| Use decentralized mean-field Q-learning with an estimated current mean field rather than a previous global mean field | Mean-field reinforcement learning · Battle | percentage of games won | Helped |
| Use decentralized mean-field Q-learning for heterogeneous agents | Combined Arms · Combined Arms | performance | Helped |
| Use decentralized mean-field Q-learning with current opponent-strategy estimates | Mean-field reinforcement learning · Gather | average reward | Helped |
| Use decentralized mean-field Q-learning with current opponent-strategy estimates | Mean-field reinforcement learning · Gather | percentage of games won | Helped |
| Use current rather than previous mean-field information | Mean-field reinforcement learning · Tiger-Deer | average reward | No clear effect |
| Use decentralized mean-field Q-learning | Mean-field reinforcement learning · Tiger-Deer | number of deer killed | Helped |
| Use decentralized mean-field actor-critic | Actor-critic reinforcement learning · Waterworld | performance | Helped |
| Model the current mean-field distribution of ride requests | Ride-pool matching · Ride-pool Matching Problem test set | service rate | Helped |
| Increase the number of vehicles | Ride-pool matching · Ride-pool Matching Problem | service rate: N varied from 80 to 120 | Helped |
Closest papers by meaning
- Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Major-Minor Mean Field Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.89)
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics (NeurIPS 2025 · similarity 0.89)
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (ICLR 2024 · similarity 0.89)
- Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games (ICML 2025 · similarity 0.88)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.88)
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.