Research map / Multi-agent systems and games / Cooperative multi-agent RL
HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning
Hu Fu, Pengyi Li, Hao Chen, Xuanyu Xiang, Biao Luo, Yihua Tan
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 the Riemannian Backbone (direction sharing) (ablation) | HPS (QMIX) · SMACv1 5m_vs_6m, MMM2 and VMAS sampling | median win rate / return | Improved |
| add the Agent-Specific Scale Generator (ablation) | HPS (QMIX) · SMACv1 5m_vs_6m, MMM2 and VMAS sampling | median win rate / return | Improved |
| apply HPS to VDN, QMIX and QPLEX mixers | value-mixing networks · VMAS (5m_vs_6m, MMM2, Sampling) | median win rate / return | Improved |
| use HPS instead of full parameter sharing in Zerg SMACv2 scenarios | FuPS · SMACv2 Zerg | median win rate | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Kaleidoscope — Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning (NeurIPS 2024) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing (ICML 2021 · similarity 0.91)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 2025 · similarity 0.90)
- Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- GradPS: Resolving Futile Neurons in Parameter Sharing Network for Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.87)
- Optimistic Multi-Agent Policy Gradient (ICML 2024 · similarity 0.85)
- Learning to Share: Selective Memory for Efficient Parallel Agentic Systems (ICML 2026 · 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.
