Personal Knowledge Base

A long-term research and learning notebook for posts, notes, papers, projects, and research directions.

Skip to content
← Back to blog

Bellman Optimality as a Planning Lens

A compact note on why the Bellman equation is more than a recurrence: it is a way to organize decisions under uncertainty.

1 min read

The recursive view

The Bellman optimality equation separates a decision into an immediate reward and the value of what follows:

V(s)=maxaE[r+γV(s)s,a]V^*(s)=\max_a \mathbb{E}[r+\gamma V^*(s') \mid s,a]

That decomposition is useful whenever a long-horizon problem can be expressed as a sequence of smaller state transitions.

Why it matters for learned agents

In a learned system, the state is often a representation rather than a raw observation. The quality of planning therefore depends on both the transition model and the representation used to preserve information that matters for future decisions.

The practical lesson is simple: before tuning an optimizer, ask whether the state contains the variables that make the future predictable.

A working checklist

  1. Define the state and action spaces explicitly.
  2. Identify which information is lost by the representation.
  3. Compare one-step prediction quality with long-horizon planning quality.

A useful value function is a compressed account of consequences, not just a score attached to a state.

Related Posts