Flight Lab / Learning machines / 03

Lesson 03 of 06 · about 5 min

Solve the backup

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

The Bellman equation writes a state value as the best immediate reward plus the discounted value of the next state. When the next state is the same state, the equation closes on one unknown.

One action pays 4 and returns to the same state. Gamma is 0.5. Enter V.

On the Knowledge page

Resources