rahualrai / deepracer_floridamen Goto Github PK
View Code? Open in Web Editor NEWDeep Racer in Howard University. Uses a reward function that prioritized staying on the track and following the correct direction. Hyperparameters including batch size, discount factor, and loss type were optimized to achieve a first-place finish. The project combined reinforcement learning and robotics through the DeepRacer platform
License: MIT License