Reward Shaping Study for Sub-Goal Based Robotic Tasks

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2022

Autores

Antão, L (Autor) Outra; Santos, L (Autor) Outra; Reis, J (Autor) Outra; Gil Manuel Gonçalves (Autor) FEUP

Ata de Conferência Internacional

Título: 2022 2nd International Conference on Robotics, Automation and Artificial Intelligence, RAAI 2022

Páginas: 74-79

2nd International Conference on Robotics, Automation and Artificial Intelligence, RAAI 2022

9 December 2022 through 11 December 2022

Indexação

Scopus

Outras Informações

ID Authenticus: P-00Y-C07

DOI: 10.1109/raai56146.2022.10092972

Abstract (EN): Robotics has been providing essential tools to improve the Industry's flexibility and reconfiguration. Nowadays, the tasks are highly complex, making it mandatory to renew programming techniques and craft sophisticated solutions. This is where Reinforcement Learning comes in handy: it broadens the horizon for new and disruptive methodologies, incorporating tolerance to uncertainties using exploration. However, those solutions can be challenging when it comes to building the reward function. So, this work proposes a ''divide and conquer'' approach, which transforms a long and complex task into smaller and easier achieved goals that boosts training efficiency and performance. This study tested different combinations of parameters and proposes a set of guidelines that used a Pickand-Place environment. The observed performance shows higher success rates and faster convergence for two and three sub-goals when comparing the sub-goal approach versus a sequential and traditional reward. © 2022 IEEE.

Idioma: Inglês

Tipo (Avaliação Docente): Científica