Glossary term
Glossary term
Agentic Systems
In reinforcement learning, the function that predicts the expected return from taking an action in a state and then following a given policy.
Q-function is also known as state-action value function.
Created for this library
A logistics RL team uses a Q-function to estimate the expected long-run reward of dispatching to each candidate next stop.
A trading research team uses a Q-function to estimate the expected long-run revenue of each bid action.
An energy company uses a Q-function in its HVAC RL agent to estimate the value of each setpoint change.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License