Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis.
Assaf HallakAviv TamarRémi MunosShie MannorPublished in: AAAI (2016)
Keyphrases
- temporal difference learning
- function approximation
- reinforcement learning
- fixed point
- bias variance analysis
- evaluation function
- game playing
- temporal difference
- machine learning
- reinforcement learning algorithms
- neural network
- genetic programming
- bias variance
- learning algorithm
- policy iteration
- markov decision process
- gaussian process
- sufficient conditions
- step size
- ensemble methods
- learning tasks
- dynamical systems