Learning Policies for Neural Network Architecture Optimization Using Reinforcement Learning.
Raghav VadheraManfred HuberPublished in: FLAIRS (2023)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- machine learning
- policy gradient methods
- learning systems
- learning agents
- temporal difference learning
- policy search
- supervised learning
- optimal policy
- active learning
- function approximation
- learning capabilities
- markov decision process
- kernel machines
- multiagent reinforcement learning
- relational reinforcement learning
- macro actions
- prior knowledge