the.ai

Reinforcement / Foundations

verified

Bellman Equation

The value of where you are is the reward you get now plus the value of where you end up. Written down, that sentence is the whole of dynamic programming and the thing every method in this domain is approximating — it turns a question about an infinite future into a relationship between adjacent moments.

Viz primitive · budget-splitdiscounted-tail = 8

discounted-tail holds 29% of the budget; rest holds the remaining 71%.

Value the discount assigns to the far future, against the value of the next few steps, in equal units. Drag the discounted tail up to watch the horizon lengthen — at the far right the contraction weakens, which is where the guarantee that this converges runs out.

8

Reviewed by opendroid · 2026-08-18

  • arXiv:1312.5602 — Playing Atari with Deep Reinforcement Learning
  • arXiv:1506.02438 — High-Dimensional Continuous Control Using Generalized Advantage Estimation

Origin · not linkable

  • Bellman 1957 — Dynamic Programming · Princeton University Press · doi:10.1515/9781400835386