Learning and planning in environments with delayed feedback.
Thomas J. WalshAli NouriLihong LiMichael L. LittmanPublished in: Auton. Agents Multi Agent Syst. (2009)
Keyphrases
- search algorithm
- learning systems
- learning algorithm
- delayed feedback
- learning process
- active learning
- motion planning
- learning problems
- decision theoretic
- domain independent
- explanation based learning
- action selection
- online learning
- macro operators
- search control rules
- distributed learning
- macro actions
- data sets
- learning scheme
- learning tasks
- dynamic environments
- decision support
- training set
- support vector
- reinforcement learning
- machine learning
- neural network