2 papers
cs.AI2026
Learning-Augmented Online Allocation under Unreliable Advice: Robustness, Exposure Fairness, and Distribution Shift
Fredy Pokou
Learning-augmented algorithms improve online decisions using predictions, but unreliable advice may harm efficiency and fairness. We study an online allocation problem with finite…
cs.LG2026
Low-Complexity Policy Tessellations in Structured Markov Decision Processes
Fredy Pokou
We study optimal-policy geometry in structured Markov decision processes. While approximate dynamic programming and reinforcement learning typically approximate high-dimensional va…