Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning.
Renata Garcia OliveiraWouter CaarlsPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- online learning
- ensemble learning
- real time
- learning algorithm
- state space
- machine learning
- online communities
- parameter settings
- ensemble methods
- markov decision processes
- cross validation
- dynamic programming
- base classifiers
- weighted graph
- social media
- gaussian process
- balancing exploration and exploitation