Maximizing Ensemble Diversity in Deep Reinforcement Learning.
Hassam SheikhMariano PhielippLadislau BölöniPublished in: ICLR (2022)
Keyphrases
- reinforcement learning
- classifier ensemble
- learning algorithm
- ensemble members
- diversity measures
- function approximation
- ensemble methods
- ensemble learning
- ensemble feature selection
- model free
- optimal policy
- random forests
- neural network
- machine learning
- random forest
- training data
- markov decision processes
- action selection
- training set
- temporal difference
- reinforcement learning algorithms
- state space
- learning process
- multi agent
- deep learning
- function approximators
- temporal difference learning
- policy gradient
- multi agent reinforcement learning
- base classifiers
- neural network ensemble
- multi class