6 papers
MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
Chengqi Zheng, Jianda Chen, Yueming Lyu +5
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven constructio…
Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
Wen Zheng Terence Ng, Jianda Chen, Yuan Xu +1
This work addresses the challenge of personalizing trajectories generated in automated decision-making systems by introducing a resource-efficient approach that enables rapid adapt…
Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration
Chengqi Zheng, Haiyan Yin, Jianda Chen +3
Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as ag…
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
Jianda Chen, Wen Zheng Terence Ng, Zichen Chen +2
In reinforcement learning with image-based inputs, it is crucial to establish a robust and generalizable state representation. Recent advancements in metric learning, such as deep…
Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
Ng Wen Zheng Terence, Chen Jianda
This paper presents Dual Action Policy (DAP), a novel approach to address the dynamics mismatch inherent in the sim-to-real gap of reinforcement learning. DAP uses a single policy…
Off-dynamics Conditional Diffusion Planners
Wen Zheng Terence Ng, Jianda Chen, Tianwei Zhang
Offline Reinforcement Learning (RL) offers an attractive alternative to interactive data acquisition by leveraging pre-existing datasets. However, its effectiveness hinges on the q…