Temporal Difference Control within a Dynamic Environment.
Leo GalwayDarryl CharlesMichaela M. BlackColin FyfePublished in: GAMEON (2007)
Keyphrases
- dynamic environments
- temporal difference
- reinforcement learning algorithms
- adaptive control
- evaluation function
- action selection
- td learning
- reinforcement learning
- function approximation
- changing environment
- path planning
- mobile robot
- step size
- control system
- model free
- monte carlo
- real environment
- supervised learning
- decision making
- control strategy
- control policy
- temporal difference methods