Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Generalised Bellman recurrence and three dualities in sequential decision-making
Fernando E. Rosas, David Hyland, Daniel Polani
What gives the Bellman equation its form? We show that the recursive properties of optimal value functions follow from three conditions: that the dynamics decomposes through suffic…
cs.LG2026
Adaptive state-action abstractions via rate-distortion
Fernando E. Rosas
When learning to walk, infants seem to address a coarse version of the problem first - stay upright, reach the caregiver - and refine it only when further practice at that resoluti…