Actor-critic versus direct policy search: a comparison based on sample complexity.
Arnaud de Froissard de BroissiaOlivier SigaudPublished in: CoRR (2016)
Keyphrases
- sample complexity
- theoretical analysis
- upper bound
- active learning
- supervised learning
- lower bound
- learning problems
- special case
- learning algorithm
- generalization error
- training examples
- sample size
- reinforcement learning
- function approximation
- computational complexity
- objective function
- semi supervised learning
- decision trees