TPN:Triple network algorithm for deep reinforcement learning.
Chen HanXuanyin WangPublished in: Neurocomputing (2024)
Keyphrases
- reinforcement learning
- computational complexity
- detection algorithm
- objective function
- dynamic programming
- learning algorithm
- optimization algorithm
- high accuracy
- matching algorithm
- monte carlo
- k means
- times faster
- np hard
- theoretical analysis
- artificial neural networks
- function approximation
- computational cost
- network traffic
- stochastic approximation
- simulated annealing
- worst case
- wireless sensor networks
- search space
- similarity measure
- decision trees