Addressing Lane Keeping and Intersections using Deep Conditional Reinforcement Learning.
Vítor A. S. SilvaValdir GrassiPublished in: LARS/SBR/WRE (2021)
Keyphrases
- reinforcement learning
- traffic flow
- traffic signal
- function approximation
- learning algorithm
- state space
- belief nets
- reinforcement learning algorithms
- random field model
- model free
- conditional probabilities
- traffic light
- reinforcement learning methods
- traffic control
- temporal difference
- optimal control
- multi agent
- multi agent reinforcement learning
- lane detection
- temporal difference learning
- robotic control
- data sets
- conditional logic
- control policy
- action space
- deep learning
- optimal policy
- detection algorithm
- supervised learning
- dynamic programming
- learning process
- machine learning