Q-learning and enhanced policy iteration in discounted dynamic programming

Mathematics

• Q-learning 100%
• Policy Iteration 87%
• Dynamic Programming 59%
• Look-up Table 57%
• Asynchronous Algorithms 32%
• Optimal Stopping Problem 25%
• Stochastic Algorithms 23%
• Large-scale Problems 23%
• Learning Algorithm 23%
• Function Approximation 23%
• Linear system of equations 22%
• Decision problem 20%
• Resolve 19%
• Policy 19%
• Basis Functions 19%
• Linear Function 18%
• Evaluation 14%
• Iteration 13%
• Simulation 12%
• Approximation 10%
• Form 8%

Engineering & Materials Science

• Dynamic programming 58%
• Table lookup 36%
• Linear systems 13%
• Learning algorithms 12%