A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer in Autonomous Driving

arXiv:2304.08235v2 Announce Type: replace
Abstract: Deep Reinforcement Learning (DRL) has shown remarkable success in solving complex tasks across various research fields. However, transferring DRL agents to the real world is still challenging due to the significant discrepancies between simulation and reality. To address this issue, we propose a robust DRL framework that leverages platform-dependent perception modules to extract task-relevant information and train a lane-following and overtaking agent in simulation. This framework facilitates the seamless transfer of the DRL agent to …

abstract agents arxiv autonomous autonomous driving cs.ai cs.lg cs.ro driving fields framework however issue platform reality reinforcement reinforcement learning research simulation success tasks transfer type world