Network Architecture Reasoning Via Deep Deterministic Policy Gradient.
Huidong LiuFang DuXiaofen TangHao LiuZhenhua YuPublished in: ICME (2020)
Keyphrases
- network architecture
- policy gradient
- artificial neural
- neural network
- actor critic
- reinforcement learning
- neural network model
- model free reinforcement learning
- gradient method
- approximation methods
- function approximation
- reinforcement learning algorithms
- knowledge base
- partially observable markov decision processes
- domain independent
- heuristic search
- artificial neural networks
- genetic algorithm