Q‑Table

Tabular representation of Q‑values for discrete state and action spaces.

Q‑Function

Mapping from state‑action pairs to expected returns, often approximated with neural networks.

Q‑Value

Expected return of taking an action in a state under a policy, central to Q‑learning and DQN.

Q‑Learning

Model‑free reinforcement learning algorithm that learns action‑value functions to maximize cumulative reward.

Q‑LoRA

Parameter‑efficient fine tuning approach that combines low‑rank adaptation with quantized base weights to cut VRAM use.

Quantization (AI)

Compressing model weights and activations to lower precision, for example 8‑bit or 4‑bit, to reduce memory and speed up inference.

Quadratic Voting

Voting mechanism where the cost of additional votes grows quadratically, balancing intensity and fairness.

Quadratic Funding

Public goods funding mechanism where many small donations receive higher matching than a few large ones, encouraging broad support.

Phishing

Social engineering attack where an adversary tricks a user into revealing secrets or signing malicious transactions.

NACKL News