RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes

arXiv:2405.04714v1 Announce Type: cross
Abstract: Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding catastrophic failures during training, which might severely impede both learning progress and the performance of the final policy. In many robotics settings, this amounts to avoiding certain "unsafe" states. The high-speed off-road driving task represents a particularly challenging instantiation of this problem: a high-return policy should …

abstract arxiv constraints control cs.ai cs.lg cs.ro driving framework however learn performance policies progress reinforcement reinforcement learning risk robotic through training type world