{"type":"ScholarlyArticle","title":"GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning","authors":[{"name":"Yingbo Luo","slug":"yingbo-luo","given":"Yingbo","family":"Luo","affiliation":""},{"name":"Meibao Yao","slug":"meibao-yao","given":"Meibao","family":"Yao","affiliation":""},{"name":"Xueming Xiao","slug":"xueming-xiao","given":"Xueming","family":"Xiao","affiliation":""}],"abstract":"Training a universal controller for robots with different morphologies is a promising research trend, since it can significantly enhance the robustness and resilience of the robotic system. However, diverse morphologies can yield different dimensions of state space and action space, making it difficult to comply with traditional policy networks. Existing methods address this issue by modularizing the robot configuration, while do not adequately extract and utilize the overall morphological information, which has been proven crucial for training a universal controller. To this end, we propose GCNT, a morphology-agnostic policy network based on improved Graph Convolutional Network (GCN) and Transformer. It exploits the fact that GCN and Transformer can handle arbitrary number of modules to achieve compatibility with diverse morphologies. Our key insight is that the GCN is able to efficiently extract morphology information of robots, while Transformer ensures that it is fully utilized by allowing each node of the robot to communicate this information directly. Experimental results show that our method can generate resilient locomotion behaviors for robots with different configurations, including zero-shot generalization to robot morphologies not seen during training. In particular, GCNT achieved the best performance on 8 tasks in the 2 standard benchmarks.","doi":"10.24963/ijcai.2025/972","url":"https://ijcai.org/proceedings/2025/972","pdf":"https://ijcai.org/proceedings/2025/0972.pdf","markdown":"https://ijcai.org/proceedings/2025/972.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/972","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Robotics","track":"Main Track","number":972,"pages":{"first":8741,"last":8749},"keywords":["Robotics: ROB: Learning in robotics","Robotics: ROB: Behavior and control"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}