no code implementations • 11 Dec 2022 • Altun Rzayev, Vahid Tavakol Aghaei
In this study, three reinforcement learning algorithms; DDPG, TD3 and SAC have been used to train Fetch robotic manipulator for four different tasks in MuJoCo simulation environment.
no code implementations • 7 Sep 2022 • Vahid Tavakol Aghaei, Arda Ağababaoğlu, Biram Bawo, Peiman Naseradinmousavi, Sinan Yildirim, Serhat Yeşilyurt, Ahmet Onat
Our MCMC-based RL algorithm is a model-free and gradient-free algorithm, in which the designer does not have to know the precise dynamics of the plant and its uncertainties.