Feature-based aggregation and deep reinforcement learning: A survey and some new implementations

Mathematics

• Reinforcement Learning 100%
• Aggregation 66%
• Policy 48%
• Policy Iteration 48%
• Decision problem 33%
• Neural Networks 31%
• Iteration Method 17%
• Nonlinear Function 16%
• Cost Function 16%
• Linear Function 15%
• Approximate Solution 12%

Engineering & Materials Science

• Reinforcement learning 66%
• Agglomeration 57%
• Deep neural networks 16%
• Cost functions 15%
• Neural networks 10%