Efficient learning of safe driving policy via human-ai copilot optimization

Q Li, Z Peng, B Zhou - arXiv preprint arXiv:2202.10341, 2022 - arxiv.org
Human intervention is an effective way to inject human knowledge into the training loop of
reinforcement learning, which can bring fast learning and ensured training safety. Given the …
被引用次数：32 相关文章

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

Q Li, Z Peng, B Zhou - International Conference on Learning … - openreview.net
Human intervention is an effective way to inject human knowledge into the training loop of
reinforcement learning, which can bring fast learning and ensured training safety. Given the …

Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization

Q Li, Z Peng, B Zhou - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Human intervention is an effective way to inject human knowledge into the training loop of
reinforcement learning, which can bring fast learning and ensured training safety. Given the …