Currently developing expertise in machine learning, focusing on transfer learning and reinforcement learning algorithms like DDPG to adapt robotic locomotion from land to water. Designing and simulating robot models using Gazebo and ROS, with ongoing efforts to optimize training time and improve performance metrics such as stability and gait control. Proficient in Python, PyTorch, TensorFlow and simulation tools, with a strong focus on leveraging simulation environments to explore adaptive robotic systems. Research aims to demonstrate the potential of transfer learning for efficient adaptation in diverse and challenging environments.