Autonomous Vehicles promise to transport people in a safer, accessible, and even efficient way. Nowadays, real-world autonomous vehicles are build by large teams from big companies with a tremendous amount of engineering effort. Deep Reinforcement Learning can be used instead, without domain experts, to learn end-to-end driving policies. Here, we combine Curriculum Learning with deep reinforcement learning, in order to learn without any prior domain knowledge, an end-to-end competitive driving policy for the CARLA autonomous driving simulator. To our knowledge, this is the first work which provides consistent results of our driving policy on all the town scenarios provided by CARLA. Moreover, we point out two important issues in reinforcement learning: the former is about learning the value function in a stable way, whereas the latter is related to normalizing the learned advantage function. A proposal of a solution to these problems is provided.
REINFORCED CURRICULUM LEARNING FOR AUTONOMOUS DRIVING IN CARLA / Anzalone, L.; Barra, S.; Nappi, M.. - 2021-:(2021), pp. 3318-3322. (Intervento presentato al convegno 2021 IEEE International Conference on Image Processing, ICIP 2021 tenutosi a usa nel 2021) [10.1109/ICIP42928.2021.9506673].
REINFORCED CURRICULUM LEARNING FOR AUTONOMOUS DRIVING IN CARLA
Barra S.;Nappi M.
2021
Abstract
Autonomous Vehicles promise to transport people in a safer, accessible, and even efficient way. Nowadays, real-world autonomous vehicles are build by large teams from big companies with a tremendous amount of engineering effort. Deep Reinforcement Learning can be used instead, without domain experts, to learn end-to-end driving policies. Here, we combine Curriculum Learning with deep reinforcement learning, in order to learn without any prior domain knowledge, an end-to-end competitive driving policy for the CARLA autonomous driving simulator. To our knowledge, this is the first work which provides consistent results of our driving policy on all the town scenarios provided by CARLA. Moreover, we point out two important issues in reinforcement learning: the former is about learning the value function in a stable way, whereas the latter is related to normalizing the learned advantage function. A proposal of a solution to these problems is provided.File | Dimensione | Formato | |
---|---|---|---|
Reinforced_Curriculum_Learning_For_Autonomous_Driving_In_Carla.pdf
solo utenti autorizzati
Tipologia:
Versione Editoriale (PDF)
Licenza:
Accesso privato/ristretto
Dimensione
560.75 kB
Formato
Adobe PDF
|
560.75 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.