ProLoNets: Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement Learning.
Andrew SilvaMatthew C. GombolayPublished in: CoRR (2019)
Keyphrases
- human experts
- domain knowledge
- reinforcement learning
- domain experts
- domain specific knowledge
- fitted q iteration
- network architecture
- neural network
- function approximation
- state space
- post processing
- domain specific
- knowledge acquisition
- background knowledge
- reinforcement learning methods
- domain theory
- learning process
- data analysis
- data sets
- previously learned
- sensory inputs
- machine learning
- decision trees
- training data
- domain independent
- classification algorithm
- knn