Deep Reinforcement Learning for Humanoid Robot Dribbling**Alexandre Muzio acknowledges CAPES for his scholarship (number 88882.161989/2017-01). Takashi Yoneyama would like to thank CNPq - National Research Council of Brasil for the grant 304134/2-18-0. The authors thank ITAndroids' sponsors: Altium, Cenic, Intel, ITAEx, MathWorks, Metinjo, Micropress, Polimold, Rapid, SolidWorks, STMicroelectronics, Wildlife Studios, and Virtual.PYXIS

Alexandre F. V. Muzio, Marcos R. O. A. Máximo, Takashi Yoneyama. Deep Reinforcement Learning for Humanoid Robot Dribbling**Alexandre Muzio acknowledges CAPES for his scholarship (number 88882.161989/2017-01). Takashi Yoneyama would like to thank CNPq - National Research Council of Brasil for the grant 304134/2-18-0. The authors thank ITAndroids' sponsors: Altium, Cenic, Intel, ITAEx, MathWorks, Metinjo, Micropress, Polimold, Rapid, SolidWorks, STMicroelectronics, Wildlife Studios, and Virtual.PYXIS. In Luiz Marcos Garcia Gonçalves, Paulo Lilles Jorge Drews Junior, Bruno Marques Ferreira da Silva, Davi Henrique dos Santos, Julio César Paulino de Melo, Carla da Costa Fernandes Curvelo, João Alberto Fabro, editors, Latin American Robotics Symposium, Brazilian Symposium on Robotics, and Workshop on Robotics in Education, LARS/SBR/WRE 2020, Natal, Brazil, November 9-12, 2020. pages 1-6, IEEE, 2020. [doi]