Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring.
Erwan LecarpentierSebastian RappMarc MeloEmmanuel RachelsonPublished in: CoRR (2017)
Keyphrases
- empirical evaluation
- model free
- reinforcement learning algorithms
- reinforcement learning
- learning algorithm
- rl algorithms
- function approximation
- policy evaluation
- temporal difference
- active learning
- machine learning
- policy iteration
- machine learning algorithms
- learning problems
- learning tasks
- training examples
- supervised learning
- robotic systems
- learning process
- training data
- average reward
- data sets
- optimal policy
- state space
- learning rate
- data points
- multi agent
- decision trees