Deep reinforcement learning with a critic-value-based branch tree for the inverse design of two-dimensional optical devices.
Hyo-Seok HwangMinhyeok LeeJunhee SeokPublished in: Appl. Soft Comput. (2022)
Keyphrases
- reinforcement learning
- three dimensional
- design principles
- case study
- user interface
- dynamic programming
- embedded systems
- genetic algorithm
- multi dimensional
- function approximation
- index structure
- tree structures
- machine learning
- temporal difference
- action selection
- tree structure
- building blocks
- knowledge based systems
- supervised learning
- multi agent