Discrete Control in Real-World Driving Environments using Deep Reinforcement Learning
This work addresses the problem of inefficient training for self-driving cars due to reliance on simulators, offering a method for real-world deployment with reduced data and computational needs, though it appears incremental as it builds on existing RL algorithms.
The paper tackles the challenge of training self-driving cars efficiently in real-world environments by introducing a framework that converts real-world driving into a gaming environment using a reliable MDP and proposes variations of RL algorithms in a multi-agent setting, resulting in the multi-agent setting outperforming single-agent in all scenarios with minimal input video data and training.
Training self-driving cars is often challenging since they require a vast amount of labeled data in multiple real-world contexts, which is computationally and memory intensive. Researchers often resort to driving simulators to train the agent and transfer the knowledge to a real-world setting. Since simulators lack realistic behavior, these methods are quite inefficient. To address this issue, we introduce a framework (perception, planning, and control) in a real-world driving environment that transfers the real-world environments into gaming environments by setting up a reliable Markov Decision Process (MDP). We propose variations of existing Reinforcement Learning (RL) algorithms in a multi-agent setting to learn and execute the discrete control in real-world environments. Experiments show that the multi-agent setting outperforms the single-agent setting in all the scenarios. We also propose reliable initialization, data augmentation, and training techniques that enable the agents to learn and generalize to navigate in a real-world environment with minimal input video data, and with minimal training. Additionally, to show the efficacy of our proposed algorithm, we deploy our method in the virtual driving environment TORCS.