A Multi-sensing Input and Multi-constraint Reward Mechanism Based Deep Reinforcement Learning Method for Self-driving Policy Learning.
Zhongli WangHao WangXin CuiChaochao ZhengPublished in: ICIRA (4) (2021)
Keyphrases
- reinforcement learning
- policy search
- unsupervised learning
- input data
- objective function
- learning mechanism
- learning process
- supervised learning
- state action
- support vector machine
- dynamic programming
- prior knowledge
- learning algorithm
- multi agent
- policy gradient
- state space
- neural network
- optimal policy
- markov decision processes
- evaluation function
- function approximators
- machine learning