L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning.
Keith G. MillsFred X. HanMohammad SalamehSeyed Saeed Changiz RezaeiLinglong KongWei LuShuo LianShangling JuiDi NiuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning problems
- learning process
- policy search
- neural architectures
- supervised learning
- learning tasks
- reinforcement learning algorithms
- robot control
- optimal solution
- mobile robot
- evolutionary computation
- machine learning
- function approximation
- learning scheme
- model free
- motor control
- continuous state