Optimizing Robotic Arm Control Using Deep Deterministic Policy Gradient: An Exploration of Hyperparameter Tuning

Computing Science, University of Alberta, T6G 2E8 Edmonton, Canada

^* Corresponding author: yile@ualberta.ca

Abstract

Robotic arms are essential in a wide range of applications, from industrial automation to medical surgeries, where both accuracy and adaptability are critical. Traditional path-planning methods for robotic arms, such as Rapidly-exploring Random Trees (RRT) and Probabilistic Roadmaps (PRM), often suffer from limitations in dynamic environments. Reinforcement Learning (RL) presents a promising alternative for optimizing robotic arm control by enabling adaptive learning through trial and error. This study focuses on the application of Deep Deterministic Policy Gradient (DDPG), a popular RL algorithm, to control a simulated robotic arm following a mouse pointer. The study investigates the impact of three key hyperparameters—learning rate, batch size, and memory capacity—on the performance of the DDPG model. This paper systematically tested multiple values for each parameter and evaluated the model's success rate and average time per goal. Results showed that the optimal combination of parameters was a learning rate of 0.001, a batch size of 50, and a memory capacity of 30,000, yielding a success rate of 76.00% and an average time per goal of 0.07 seconds. These results emphasize the significance of fine-tuning hyperparameters to achieve optimal performance in robotic control tasks. Future work will focus on exploring adaptive hyperparameter tuning strategies and applying these methods to more complex and dynamic robotic environments to further enhance performance and adaptability.