From Q(lambda) to Average Q-learning: Efficient Implementation of an Asymptotic Approximation.
Frédérick GarciaFlorent SerrePublished in: IJCAI (2001)
Keyphrases
- efficient implementation
- relative error
- marginal likelihood
- learning algorithm
- reinforcement learning
- active set
- efficient processing
- hardware implementation
- cooperative
- state space
- error bounds
- function approximation
- model selection
- multi agent
- approximation algorithms
- queueing networks
- reinforcement learning algorithms
- fixed point
- learning rate
- confidence intervals
- model free
- collaborative filtering
- motion estimation
- central limit theorem