Supervised pre-training for improved stability in deep reinforcement learning.
Sooyoung JangHyung-Il KimPublished in: ICT Express (2023)
Keyphrases
- reinforcement learning
- supervised learning
- learning algorithm
- machine learning
- function approximation
- supervised methods
- optimal policy
- deep learning
- training process
- test set
- unsupervised learning
- state space
- learning process
- training set
- multi agent
- training examples
- transfer learning
- learning tasks
- hidden markov models
- training stage
- restricted boltzmann machine
- supervised training
- deep architectures