MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909736758149120 |
|---|---|
| author | Liu, Qi Zhang, Xiaopeng Tan, Mingshan Ma, Shuaikang Ding, Jinliang Li, Yanjie |
| author_facet | Liu, Qi Zhang, Xiaopeng Tan, Mingshan Ma, Shuaikang Ding, Jinliang Li, Yanjie |
| contents | This paper proposes a novel method to enhance locomotion for a single humanoid robot through cooperative-heterogeneous multi-agent deep reinforcement learning (MARL). While most existing methods typically employ single-agent reinforcement learning algorithms for a single humanoid robot or MARL algorithms for multi-robot system tasks, we propose a distinct paradigm: applying cooperative-heterogeneous MARL to optimize locomotion for a single humanoid robot. The proposed method, multi-agent reinforcement learning for single humanoid locomotion (MASH), treats each limb (legs and arms) as an independent agent that explores the robot's action space while sharing a global critic for cooperative learning. Experiments demonstrate that MASH accelerates training convergence and improves whole-body cooperation ability, outperforming conventional single-agent reinforcement learning methods. This work advances the integration of MARL into single-humanoid-robot control, offering new insights into efficient locomotion strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_10423 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion Liu, Qi Zhang, Xiaopeng Tan, Mingshan Ma, Shuaikang Ding, Jinliang Li, Yanjie Robotics Artificial Intelligence Systems and Control This paper proposes a novel method to enhance locomotion for a single humanoid robot through cooperative-heterogeneous multi-agent deep reinforcement learning (MARL). While most existing methods typically employ single-agent reinforcement learning algorithms for a single humanoid robot or MARL algorithms for multi-robot system tasks, we propose a distinct paradigm: applying cooperative-heterogeneous MARL to optimize locomotion for a single humanoid robot. The proposed method, multi-agent reinforcement learning for single humanoid locomotion (MASH), treats each limb (legs and arms) as an independent agent that explores the robot's action space while sharing a global critic for cooperative learning. Experiments demonstrate that MASH accelerates training convergence and improves whole-body cooperation ability, outperforming conventional single-agent reinforcement learning methods. This work advances the integration of MARL into single-humanoid-robot control, offering new insights into efficient locomotion strategies. |
| title | MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion |
| topic | Robotics Artificial Intelligence Systems and Control |
| url | https://arxiv.org/abs/2508.10423 |