4 papers
Attention-based Hierarchical Variational Information Bottleneck for Robust Multi-Agent Communication under Variable Bandwidth
Lukas Koch Vindbjerg, Qi Zhang, Yury Brodskiy +1
Learning-based multi-agent communication under limited bandwidth does not only require deciding what to communicate, but also structuring messages so that partial transmissions rem…
Belief-Contraction-Driven Active Inverse Source Localization and Characterization
Yiwei Shi, Mengyue Yang, Qi Zhang +3
Active inverse source localization and characterization (ISLC) in dynamic fields requires sequential decision making under partial observability, where a mobile sensor must infer l…
Autonomous Goal Detection and Cessation in Reinforcement Learning: A Case Study on Source Term Estimation
Yiwei Shi, Muning Wen, Qi Zhang +3
Reinforcement Learning has revolutionized decision-making processes in dynamic environments, yet it often struggles with autonomously detecting and achieving goals without clear fe…
Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach
Yiwei Shi, Qi Zhang, Kevin McAreavey +1
This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with…