The action-value function is a function that represents the agent's estimate of how good it is to take action 
in state 
. It is denoted by 
. It is related to the state-value function by the following equation:
Action-value function
Get Hands-On Intelligent Agents with OpenAI Gym now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
