Learning Propositional Functions for Planning and Reinforcement Learning.
David Ellis HershkowitzJames MacGlashanStefanie TellexPublished in: AAAI Fall Symposia (2015)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning problems
- supervised learning
- action selection
- state space
- prior knowledge
- learning systems
- neural network
- dynamic programming
- domain independent
- function approximation
- stochastic domains
- model free
- autonomous learning
- learning tasks
- temporal difference learning
- predictive state representations
- active exploration
- multi valued
- learning capabilities
- solving problems
- active learning
- machine learning