Novelty search in neuroevolution for end effector positioning

• Datum: 2023
• Hauptverfasser: Vitiuk, A.Y., Doroshenko, A.Y.
• Format: Artikel
• Sprache: Ukrainisch
• Veröffentlicht: PROBLEMS IN PROGRAMMING 2023
• Schlagworte: neural network; neuroevolution; robotic arm; reinforcement learning; NEAT; novelty search; fitness function; UDC 004.89
• Online Zugang: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/581
• Назва журналу: Problems in programming

The article considers the use of the neuroevolution algorithm for neural network policies search when creating a controller for a robotic arm, in particular for the subtask of positioning the end effector. Neuro-evolution is a family of machine learning methods that use evolutionary algorithms by im...