Research map / Multi-agent systems and games / Cooperative multi-agent RL
Cooperative Heterogeneous Deep Reinforcement Learning
Han Zheng, Pengfei Wei, Jing Jiang, Guodong Long, Qinghua Lu, Chengqi Zhang
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 |
|---|---|---|---|
| combine SAC, PPO, and CEM with cooperative exploration and local-global memory | CSPC · Humanoid-v2 | max average return: 5142$\pm$133 -> 5412$\pm$239 | Improved |
| combine SAC, PPO, and CEM with cooperative exploration and local-global memory | CSPC · Ant-v2 | max average return: 3766$\pm$2359 -> 5337$\pm$220 | Improved |
| combine SAC, PPO, and CEM with cooperative exploration and local-global memory | CSPC · Walker2d-v2 | max average return: 4222$\pm$290 -> 5317$\pm$256 | Improved |
| combine SAC, PPO, and CEM with cooperative exploration and local-global memory | CSPC · Hopper-v2 | max average return: 3558 $\pm$139 -> 3619$\pm$52 | Improved |
| combine SAC, PPO, and CEM with cooperative exploration and local-global memory | CSPC · Swimmer-v2 | max average return: 274$\pm$118 -> 261$\pm$117 | Hurt |
| add cooperative exploration through policy transfer (ablation) | CSPC · Walker2d-v2 | final average performance | Improved |
| add local memory replay (ablation) | CSPC · Walker2d-v2 | final average performance | Improved |
| add global memory replay (ablation) | CSPC · Walker2d-v2 | final average performance | Improved |
| remove PPO (ablation) | CSPC · Walker2d-v2 | final average performance | Hurt |
| remove CEM (ablation) | CSPC · Walker2d-v2 | final average performance | Hurt |
| remove SAC (ablation) | CSPC · Walker2d-v2 | final average performance | Hurt |
| use three SAC agents with cooperative exploration and local-global memory instead of heterogeneous agents (ablation) | CHDRL · Walker2d-v2 | final average performance | Hurt |
Closest papers by meaning
- Heterogeneous Agent Collaborative Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration (ICML 2025 · similarity 0.88)
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.87)
- Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems (NeurIPS 2026 · similarity 0.87)
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL (NeurIPS 2025 · similarity 0.87)
- ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (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.
