Praxis — An adaptive tutor that shows its working Guest learner

AGI Agents (6-week course) › W2 · MDPs & value functions

0/0 this session +0 XP
Numeric Easy discountingreturn ~45s

An agent receives rewards 0, 0 and then +10 on its first three steps, and the episode ends. With γ = 0.9, what is the discounted return from the start, G = r₁ + γ·r₂ + γ²·r₃? Give your answer to 1 decimal place.

Fractions, decimals and π are all understood.

Hints are free to take and they are counted. A correct answer after two hints moves your mastery less than one without — which is the honest way to score it.

Why this question? this skill is new to you; the difficulty is about right — roughly 79% chance you get it; and it needs calibrating — few people have tried it Predicted chance you get it: 79% — the selector aims at 78%.
difficulty fit 0.999
skill need 0.75
review boost 0
calibration bonus 0.12
recency penalty 0
repetition penalty 0
frustration 0