Off-Policy Shaping Ensembles in Reinforcement Learning.
Anna HarutyunyanTim BrysPeter VrancxAnn NowéPublished in: ECAI (2014)
Keyphrases
- reinforcement learning
- reward shaping
- decision trees
- state space
- multi agent
- model free
- function approximation
- machine learning
- learning algorithm
- complex domains
- partially observable
- transfer learning
- markov decision processes
- ensemble methods
- reinforcement learning algorithms
- ensemble learning
- learning problems
- dynamic programming
- data mining
- random forests
- learning classifier systems
- optimal policy
- training data
- robot control
- learning agent
- genetic algorithm
- robotic control
- neural network ensembles