Is Q-learning provably efficient?

Computer Science

• And-States 100%
• Reinforcement Learning 100%
• Function Value 50%
• Model-Free Reinforcement Learning 50%
• Fundamental Question 50%
• Deep Reinforcement Learning 50%

Mathematics

• Function Value 100%
• Total Number 100%
• Sample Efficiency 100%

Keyphrases

• Episodic MDP 33%