Enhanced Deep Q-Learning for 2D Self-Driving Cars: Implementation and Evaluation on a Custom Track Environment
This work addresses the challenge of autonomous navigation in simulated environments, but it is incremental as it modifies an existing DQN method for a specific custom track.
The researchers tackled the problem of improving self-driving car performance in a 2D custom track environment by implementing a Deep Q-Learning Network (DQN) with a priority-based action selection mechanism, resulting in an average reward of around 40, which is approximately 60% higher than the original DQN and 50% higher than a vanilla neural network.
This research project presents the implementation of a Deep Q-Learning Network (DQN) for a self-driving car on a 2-dimensional (2D) custom track, with the objective of enhancing the DQN network's performance. It encompasses the development of a custom driving environment using Pygame on a track surrounding the University of Memphis map, as well as the design and implementation of the DQN model. The algorithm utilizes data from 7 sensors installed in the car, which measure the distance between the car and the track. These sensors are positioned in front of the vehicle, spaced 20 degrees apart, enabling them to sense a wide area ahead. We successfully implemented the DQN and also a modified version of the DQN with a priority-based action selection mechanism, which we refer to as modified DQN. The model was trained over 1000 episodes, and the average reward received by the agent was found to be around 40, which is approximately 60% higher than the original DQN and around 50% higher than the vanilla neural network.