5 papers
Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents
Chengyang Gu, Le Zhang, Jingbo Zhou +6
Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diverse digital environments, wher…
A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic
Chengyang Gu, Yuxin Pan, Hui Xiong +1
Model-based reinforcement learning (MBRL) improves sample efficiency by leveraging learned dynamics models for policy optimization. However, the effectiveness of methods such as ac…
STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order
Chengyang Gu, Yuxin Pan, Hui Xiong +1
Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tas…
Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP
Yuxin Pan, Zhiguang Cao, Chengyang Gu +4
Existing neural methods for multi-task vehicle routing problems (VRPs) typically learn unified solvers to handle multiple constraints simultaneously. However, they often underutili…
SEAL: SEmantic-Augmented Imitation Learning via Language Model
Chengyang Gu, Yuxin Pan, Haotian Bai +2
Hierarchical Imitation Learning (HIL) is a promising approach for tackling long-horizon decision-making tasks. While it is a challenging task due to the lack of detailed supervisor…