On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning.
Shiro TakagiPublished in: CoRR (2022)
Keyphrases
- optimal policy
- reinforcement learning
- markov decision processes
- state space
- multi modal
- supervised learning
- fuzzy logic
- training process
- function approximation
- real time
- medical images
- reinforcement learning algorithms
- model free
- training phase
- fault diagnosis
- multimedia
- learning algorithm
- multi agent
- training algorithm
- feature selection
- neural network