Multi-Task Lane-Free Driving Strategy for Connected and Automated Vehicles: A Multi-Agent Deep Reinforcement Learning Approach.
Mehran BerahmanMajid Rostami-ShahrbabakiKlaus BogenbergerPublished in: CoRR (2024)
Keyphrases
- multi task
- reinforcement learning
- multi agent
- multi task learning
- transfer learning
- learning problems
- traffic flow
- learning tasks
- multitask learning
- multi class
- multiple tasks
- driving simulator
- traffic signal
- traffic accidents
- gaussian processes
- learning algorithm
- feature selection
- supervised learning
- vehicle detection
- information gain
- machine learning
- intelligent vehicles
- unsupervised learning
- knowledge discovery
- prior knowledge
- image segmentation
- data sets