Motion planning for autonomous driving: The state of the art and future perspectives
Intelligent vehicles (IVs) have gained worldwide attention due to their increased
convenience, safety advantages, and potential commercial value. Despite predictions of …
convenience, safety advantages, and potential commercial value. Despite predictions of …
Deep reinforcement learning in smart manufacturing: A review and prospects
To facilitate the personalized smart manufacturing paradigm with cognitive automation
capabilities, Deep Reinforcement Learning (DRL) has attracted ever-increasing attention by …
capabilities, Deep Reinforcement Learning (DRL) has attracted ever-increasing attention by …
Video pretraining (vpt): Learning to act by watching unlabeled online videos
Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for
training models with broad, general capabilities for text, images, and other modalities …
training models with broad, general capabilities for text, images, and other modalities …
End-to-end autonomous driving: Challenges and frontiers
The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …
A survey on trajectory-prediction methods for autonomous driving
In order to drive safely in a dynamic environment, autonomous vehicles should be able to
predict the future states of traffic participants nearby, especially surrounding vehicles, similar …
predict the future states of traffic participants nearby, especially surrounding vehicles, similar …
Principled reinforcement learning with human feedback from pairwise or k-wise comparisons
We provide a theoretical framework for Reinforcement Learning with Human Feedback
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
(RLHF). We show that when the underlying true reward is linear, under both Bradley-Terry …
Dataset distillation by matching training trajectories
Dataset distillation is the task of synthesizing a small dataset such that a model trained on
the synthetic set will match the test accuracy of the model trained on the full dataset. In this …
the synthetic set will match the test accuracy of the model trained on the full dataset. In this …
Eureka: Human-level reward design via coding large language models
Large Language Models (LLMs) have excelled as high-level semantic planners for
sequential decision-making tasks. However, harnessing them to learn complex low-level …
sequential decision-making tasks. However, harnessing them to learn complex low-level …
[PDF][PDF] 生成式对抗网络GAN 的研究进展与展望
王坤峰, 苟超, 段艳杰, 林懿伦, 郑心湖, 王飞跃 - 自动化学报, 2017 - researchgate.net
摘要生成式对抗网络GAN (Generative adversarial networks) 目前已经成为人工智能学界一个
热门的研究方向. GAN 的基本思想源自博弈论的二人零和博弈, 由一个生成器和一个判别器构成 …
热门的研究方向. GAN 的基本思想源自博弈论的二人零和博弈, 由一个生成器和一个判别器构成 …
Behavior Transformers: Cloning modes with one stone
NM Shafiullah, Z Cui… - Advances in neural …, 2022 - proceedings.neurips.cc
While behavior learning has made impressive progress in recent times, it lags behind
computer vision and natural language processing due to its inability to leverage large …
computer vision and natural language processing due to its inability to leverage large …