Hierarchical Training of Deep Ensemble Policies for Reinforcement Learning in Continuous Spaces.
Gang ChenVictoria HuangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- hierarchical reinforcement learning
- training set
- fitted q iteration
- neural network
- supervised learning
- training process
- markov decision process
- training data
- policy search
- action space
- function approximation
- deep architectures
- training samples
- learning algorithm
- control policies
- ensemble methods
- deep learning
- training examples
- discrete data
- control policy
- data sets
- continuous state and action spaces
- reinforcement learning agents
- multi agent
- multiple layers
- restricted boltzmann machine
- learning process
- mobile robot
- state space
- optimal control
- learning problems
- markov decision processes
- feature selection