Avoidance Navigation Based on Offline Pre-Training Reinforcement Learning.
Wenkai YangRuihang JiYuxiang ZhangHao LeiZijie ZhaoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- supervised learning
- real time
- test set
- neural network
- machine learning
- reinforcement learning algorithms
- training set
- action space
- training phase
- function approximation
- training samples
- state space
- learning algorithm
- training examples
- collaborative learning
- markov decision processes
- training process
- search engine
- genetic algorithm