11 papers
MUTE: Return-Preserving Communication Unlearning for Efficient Multi-Agent Coordination
Rui Zuo, Qinwei Huang, Mingyang Li +3
Inter-agent communication is critical for coordinating Multi-Agent Reinforcement Learning (MARL) agents under partial observability to perform effectively in cooperative games; how…
Reasoning-aware Speculative Decoding for Efficient Vision-Language-Action Models in Autonomous Driving
Anh Dung Dinh, Simon Khan, Flora Salim
Modern Vision-Language-Action (VLA) planners for autonomous driving emit a chain-of-causation (CoC) reasoning step \emph{before} producing a trajectory. The reasoning is autoregres…
ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models
Kejing Wang, Toan Nguyen, Minh Hoang Nguyen +2
Effective online adaptation of vision-language-action (VLA) models remains challenging, as sparse rewards provide weak supervision for high-dimensional autoregressive action polici…
Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous Environments
Qinwei Huang, Rui Zuo, Simon Khan +1
Conventional federated learning assumes that greater learner participation improves training performance, by leveraging abundant, independently generated local data. However, in fe…
Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
Sanup S. Araballi, Simon Khan, Chilukuri K. Mohan
Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainab…
Predictive Auxiliary Learning for Belief-based Multi-Agent Systems
Qinwei Huang, Stefan Wang, Simon Khan +2
The performance of multi-agent reinforcement learning (MARL) in partially observable environments depends on effectively aggregating information from observations, communications,…