Learning Urban Navigation via Value Iteration Network.
Shu YangJinglin LiJie WangZhihan LiuFangchun YangPublished in: Intelligent Vehicles Symposium (2018)
Keyphrases
- infinite horizon
- long run
- dynamic programming
- state space
- online learning
- learning algorithm
- reinforcement learning
- supervised learning
- knowledge acquisition
- prior knowledge
- learning process
- active learning
- learning systems
- search algorithm
- connectionist networks
- learning tasks
- network model
- artificial neural networks
- urban planning