3 papers
cs.LG2025
Active Measuring in Reinforcement Learning With Delayed Negative Effects
Daiqi Gao, Ziping Xu, Aseel Rawashdeh +2
Measuring states in reinforcement learning (RL) can be costly in real-world settings and may negatively influence future outcomes. We introduce the Actively Observable Markov Decis…
cs.AI2025
SigmaScheduling: Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions
Asim H. Gazi, Bhanu Teja Gullapalli, Daiqi Gao +3
Timely decision making is critical to the effectiveness of mobile health (mHealth) interventions. At predefined timepoints called "decision points," intelligent mHealth systems suc…
cs.LG2025
Harnessing Causality in Reinforcement Learning With Bagged Decision Times
Daiqi Gao, Hsin-Yu Lai, Predrag Klasnja +1
We consider reinforcement learning (RL) for a class of problems with bagged decision times. A bag contains a finite sequence of consecutive decision times. The transition dynamics…