Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving.
Zhangjie CaoErdem BiyikWoodrow Z. WangAllan RaventosAdrien GaidonGuy RosmanDorsa SadighPublished in: Robotics: Science and Systems (2020)
Keyphrases
- reinforcement learning
- control policy
- control policies
- optimal policy
- control problems
- optimal control
- control system
- decentralized control
- function approximation
- markov decision process
- robot control
- policy search
- traffic accidents
- reinforcement learning algorithms
- action space
- markov decision processes
- multi agent
- robotic control
- partially observable markov decision processes
- machine learning
- adaptive control
- traffic safety
- hierarchical reinforcement learning