An Online Correction Predictive EMS for a Hybrid Electric Tracked Vehicle Based on Dynamic Programming and Reinforcement Learning.
Jinlong WuYuan ZouXudong ZhangTeng LiuZehui KongDingbo HePublished in: IEEE Access (2019)
Keyphrases
- dynamic programming
- reinforcement learning
- real time
- markov decision processes
- optimal policy
- state space
- online learning
- optimal control
- function approximation
- electric vehicles
- image sequences
- control system
- greedy algorithm
- traffic management
- temporal difference
- model free
- pedestrian detection
- coarse to fine
- stereo matching
- reinforcement learning algorithms
- linear programming
- batch mode
- learning process
- dp matching