Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble.
Gaon AnSeungyong MoonJang-Hyun KimHyun Oh SongPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- partial observability
- learning algorithm
- ensemble methods
- state space
- real time
- ensemble learning
- optimal policy
- neural network
- dynamic programming
- inherent uncertainty
- markov decision processes
- multi agent
- pruning algorithm
- policy search
- training data
- neural network ensemble
- temporal difference
- probability theory
- reinforcement learning algorithms
- temporal difference learning
- robotic control
- possibility theory
- base classifiers
- learning process
- feature selection
- machine learning