Research map / Multi-agent systems and games / Cooperative multi-agent RL
Heterogeneous Agent Q-weighted Policy Optimization
Bor-Jiun Lin, Chun-Yi Lee
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 diffusion policy instead of Gaussian policy (ablation) | HAQO · GRF 3 vs 1 with keeper | average return: 66.82 -> 97.27 | Improved |
| add diffusion policy instead of Gaussian policy (ablation) | HAQO · GRF PS | average return: 76.24 -> 92.14 | Improved |
| add diffusion policy instead of Gaussian policy (ablation) | HAQO · GRF RPS | average return: 43.27 -> 80.39 | Improved |
| add sequential updates instead of simultaneous updates (ablation) | HAQO · Bi-DexterousHands | average step reward | Improved |
| add entropy regularization surrogate (ablation) | HAQO · custom MPE two agents three landmarks | landmark coverage | Improved |
| HAQO vs HAPPO | HAQO · Multi-MuJoCo HalfCheetah-v2 2x3 | mean return: 7024 -> 6873 | No clear effect |
| HAQO vs HAPPO | HAQO · Multi-MuJoCo Humanoid-v2 17x1 | mean return: 6739 -> 7013 | Improved |
Closest papers by meaning
- Efficient Heterogeneous Exploration With Mutual Policy Divergence Maximization for Multiagent Reinforcement Learning (TPAMI 2026 · similarity 0.90)
- Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization (NeurIPS 2024 · similarity 0.88)
- Maximum Entropy Heterogeneous-Agent Reinforcement Learning (ICLR 2024 · similarity 0.88)
- Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective (NeurIPS 2025 · similarity 0.87)
- Optimistic Multi-Agent Policy Gradient (ICML 2024 · similarity 0.87)
- Towards Principled Unsupervised Multi-Agent Reinforcement Learning (NeurIPS 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.
