Learning Generalized Reactive Policies using Deep Neural Networks.
Edward GroshevAviv TamarMaxwell GoldsteinSiddharth SrivastavaPieter AbbeelPublished in: AAAI Spring Symposia (2018)
Keyphrases
- neural network
- learning systems
- deep learning
- reinforcement learning
- learning process
- active learning
- knowledge acquisition
- learning problems
- learning tasks
- background knowledge
- learning algorithm
- data sets
- unsupervised learning
- supervised learning
- semi supervised
- self organizing maps
- fuzzy logic
- function approximation
- agent architecture
- genetic algorithm
- connectionist systems