Which model-free reinforcement learning algorithm seeks to learn the value of state-action pairs and uses a Q-table to represent action values?

Which model-free reinforcement learning algorithm seeks to learn the value of state-action pairs and uses a Q-table to represent action values?

• A. Q-learning
• B. Deep Q networks (DQNs)
• C. Policy-based
• D. Model-based planning

Answer: (A)