Implementing action mask in proximal policy optimization (PPO) algorithm.
Cheng-Yen TangChien-Hung LiuWoei-Kae ChenShingchern D. YouPublished in: ICT Express (2020)
Keyphrases
- optimization algorithm
- learning algorithm
- preprocessing
- theoretical analysis
- optimization process
- detection algorithm
- experimental evaluation
- stochastic gradient
- cost function
- dynamic programming
- worst case
- optimal solution
- computational complexity
- neural network
- optimization model
- similarity measure
- recognition algorithm
- high accuracy
- k means
- np hard
- search space
- segmentation algorithm
- simulated annealing
- ant colony optimization
- times faster
- combinatorial optimization
- global optimization
- computational cost
- improved algorithm
- multi objective