Concepts / A–Z / 0–9

Concepts starting with 0–9

7 concepts, each with a plain-language explanation, examples and diagrams. Pick a letter or open a concept.

• 0-1 Loss — The multiclass categorization goal is to learn h : X → [k].
• 19-state random walk task — The λ-return is presented as a smooth alternative between Monte Carlo and one-step TD methods.
• 1D Convnets — Sequence models operate on ordered numeric representations, not raw text.
• ε-Greedy Action Selection — High initial action-value estimates can make a greedy method explore without explicitly using ε-greedy random selection.
• ε-Greedy Policies — Sarsa control estimates the action values of its current behavior policy.
• ε-soft policies — On-policy first-visit MC control alternates between episode generation and policy improvement.
• λ-Return Update Targets — The h-truncated λ-return method expands its available information one horizon at a time.