Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning.
Gabriel Victor de la CruzYunshu DuMatthew E. TaylorPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- human experts
- training set
- training process
- function approximation
- state space
- domain experts
- policy search
- motor skills
- model free
- training algorithm
- human subjects
- data sets
- training samples
- domain knowledge
- decision trees
- learning algorithm
- supervised learning
- active learning
- artificial neural networks
- human users
- training phase
- e learning
- human operators
- reinforcement learning algorithms
- machine learning