6 papers
Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
Boxuan Zhang, Weipu Zhang, Zhaohan Feng +4
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit substantial heterogeneity in both observati…
Data-driven control of network systems: Accounting for communication adaptivity and security
Gang Wang, Wenjie Liu, Yifei Li +3
Over the past decades, network systems have surged in significance, driven by merging technological advancements. These systems play pivotal roles in diverse applications ranging f…
DyMoDreamer: World Modeling with Dynamic Modulation
Boxuan Zhang, Runqing Wang, Wei Xiao +5
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-bas…
Multi-agent Embodied AI: Advances and Future Directions
Zhaohan Feng, Ruiqi Xue, Lei Yuan +7
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physica…
Data-driven Internal Model Control for Output Regulation
Wenjie Liu, Yifei Li, Jian Sun +4
Output regulation is a fundamental problem in control theory, extensively studied since the 1970s. Traditionally, research has primarily addressed scenarios where the system model…
Robust Offline Imitation Learning Through State-level Trajectory Stitching
Shuze Wang, Yunpeng Mei, Hongjie Cao +4
Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations. However, traditional IL methods are limited by their re…