Q-learning and enhanced policy iteration in discounted dynamic programming

Mathematics

• Q-learning 100%
• Policy Iteration 87%
• Dynamic Programming 59%
• Value Iteration 34%
• Optimal Stopping Problem 15%
• Large-scale Problems 14%
• Learning Algorithm 14%
• Function Approximation 14%
• Linear system of equations 13%
• Decision problem 12%
• Policy 11%
• Basis Functions 11%
• Linear Function 11%
• State Space 10%
• Contraction 10%
• Evaluation 8%
• Costs 8%
• Simulation 7%
• Standards 6%

Business & Economics

• Dynamic Programming 58%
• Optimal Stopping Problem 16%
• Policy Evaluation 15%
• Learning Algorithm 14%
• State Space 13%
• Contraction 12%
• Approximation 9%
• Simulation 8%
• Costs 4%
• Factors 4%

Engineering & Materials Science

• Dynamic programming 58%
• Linear systems 18%
• Learning algorithms 16%
• Costs 7%