A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward

The efficient design and implementation of DRL agents There has been a growing interest in self-driving cars involves many steps which are starting with state-action by the industry since Darpa Urban Challenge [1]. Despite representations, balancing multi-objective reward function, the great achievements in this competition, the deployment tuning the hyper-parameters of the optimization algorithm, of self-driving cars into production is a quite complicated deciding the network architecture, generating rich data out problem due to reasons such as long tail of edge cases, of realistic scenarios and finally broad evaluation against a safety verification and the need of intelligent algorithms that proper baseline methods with different seeds. Considering are capable of negotiating with human drivers. There are the aforementioned steps, [7] lacks the comparison with a already level-2 capable cars in production that autonomously fair baseline and uses a very naive simulation environment control the vehicle at both the longitudinal and lateral levels.