Research map / Multi-agent systems and games / Cooperative multi-agent RL
FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent 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 |
|---|---|---|---|
| Replace FOP's factorization with DOP's linear decomposition (ablation) | FOP · Max of Two Quadratic game | convergence to global optimum | Hurt |
| Replace soft policy with greedy policy (alpha = 0 during training) (ablation) | FOP · Max of Two Quadratic game | convergence to global optimum | Hurt |
| Vary team temperature annealing target (alpha-hat from 1 to 0.01) (ablation) | FOP · Non-monotonic matrix game | reaches optimal joint value 8.0 | No clear effect |
| Vary team temperature annealing approach (ablation) | FOP · Max of Two Quadratic game | convergence to global optimum | No clear effect |
| Use FOP factorized soft policy with IGO-based decomposition vs existing decomposed actor-critic methods | decomposed actor-critic · StarCraft II (2c vs 64zg, 3s vs 3z, MMM, MMM2) | test win rate | Helped |
Closest papers by meaning
- Maximum Entropy Heterogeneous-Agent Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games (ICLR 2023 · similarity 0.89)
- Value-Decomposition Multi-Agent Actor-Critics (AAAI 2021 · similarity 0.89)
- FACMAC: Factored Multi-Agent Centralised Policy Gradients (NeurIPS 2021 · similarity 0.89)
- Towards Principled Unsupervised Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.87)
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.