2 papers
cs.LG2026
Bounded-Rationality, Hedging, and Generalization
Pedro A. Ortega
A learner does not only fit data; it also determines how strongly the training sample may shape its output and how much distortion it can hedge. We study this relation as a bounded…
cs.LG2026
Notes on the Reward Representation of Posterior Updates
Pedro A. Ortega
Many ideas in modern control and reinforcement learning treat decision-making as inference: start from a baseline distribution and update it when a signal arrives. We ask when this…