Imitation is not enough: Robustifying imitation with reinforcement learning for challenging driving scenarios

Y Lu, J Fu, G Tucker, X Pan, E Bronstein… - 2023 IEEE/RSJ …, 2023 - ieeexplore.ieee.org
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data,
which can be collected at scale, to produce human-like behavior. However, policies based …
被引用次数：40 相关文章

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Y Lu, J Fu, G Tucker, X Pan, E Bronstein… - arXiv preprint arXiv …, 2022 - arxiv.org
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data,
which can be collected at scale, to produce human-like behavior. However, policies based …

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Y Lu, J Fu, G Tucker, X Pan, E Bronstein… - arXiv preprint arXiv …, 2022 - openreview.net
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data,
which can be collected at scale, to produce human-like behavior. However, policies based …

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Y Lu, J Fu, G Tucker, X Pan, E Bronstein… - arXiv e …, 2022 - ui.adsabs.harvard.edu
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data,
which can be collected at scale, to produce human-like behavior. However, policies based …
[PDF] github.io

[PDF][PDF] Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

Y Lu, J Fu, G Tucker, X Pan, E Bronstein, B Roelofs… - ml4ad.github.io
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data,
which can be collected at scale, to identify driving preferences and produce human-like …