Off-Policy Shaping Ensembles in Reinforcement Learning.
Anna HarutyunyanTim BrysPeter VrancxAnn NowéPublished in: CoRR (2014)
Keyphrases
- reinforcement learning
- reward shaping
- reinforcement learning algorithms
- function approximation
- random forests
- ensemble methods
- markov decision processes
- ensemble learning
- learning algorithm
- machine learning
- decision trees
- model free
- temporal difference
- robot control
- temporal difference learning
- neural network ensemble
- optimal policy
- hidden markov models
- neural network
- evaluation function
- transfer learning
- real robot
- markov decision problems
- policy search
- ensemble selection
- learning problems