Ensemble-based deep reinforcement learning for chatbots.
Heriberto CuayáhuitlDonghyeon LeeSeonghan RyuYongjin ChoSungja ChoiSatish Reddy IndurthiSeunghak YuHyungtak ChoiInchul HwangJihie KimPublished in: Neurocomputing (2019)
Keyphrases
- reinforcement learning
- learning algorithm
- ensemble learning
- function approximation
- neural network
- training data
- random forest
- state space
- markov decision processes
- model free
- temporal difference learning
- autonomous learning
- optimal policy
- reinforcement learning algorithms
- data sets
- training set
- random forests
- ensemble pruning
- learning capabilities
- function approximators
- action selection
- machine learning
- stochastic approximation
- reinforcement learning methods
- robotic control
- transition model
- temporal difference
- learning classifier systems
- optimal control
- ensemble methods
- prediction accuracy
- dynamic programming
- learning process
- artificial neural networks