Overtaking Maneuvers in Simulated Highway Driving using Deep Reinforcement Learning.
Meha KaushikVignesh PrasadK. Madhava KrishnaBalaraman RavindranPublished in: Intelligent Vehicles Symposium (2018)
Keyphrases
- reinforcement learning
- real robot
- function approximation
- state space
- multi agent
- learning process
- traffic safety
- supervised learning
- robotic control
- simulation model
- temporal difference
- reinforcement learning algorithms
- policy search
- temporal difference learning
- deep learning
- transfer learning
- machine learning
- car racing
- traffic accidents
- test bed
- learning problems
- optimal policy
- learning algorithm