Motion planning for autonomous driving: The state of the art and future perspectives

S Teng, X Hu, P Deng, B Li, Y Li, Y Ai… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Intelligent vehicles (IVs) have gained worldwide attention due to their increased
convenience, safety advantages, and potential commercial value. Despite predictions of …

Social interactions for autonomous driving: A review and perspectives

W Wang, L Wang, C Zhang, C Liu… - Foundations and Trends …, 2022 - nowpublishers.com
No human drives a car in a vacuum; she/he must negotiate with other road users to achieve
their goals in social traffic scenes. A rational human driver can interact with other road users …

Principled reinforcement learning with human feedback from pairwise or k-wise comparisons

B Zhu, M Jordan, J Jiao - International Conference on …, 2023 - proceedings.mlr.press
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 …

Subject-driven text-to-image generation via apprenticeship learning

W Chen, H Hu, Y Li, N Ruiz, X Jia… - Advances in …, 2024 - proceedings.neurips.cc
Recent text-to-image generation models like DreamBooth have made remarkable progress
in generating highly customized images of a target subject, by fine-tuning an``expert …

Eureka: Human-level reward design via coding large language models

YJ Ma, W Liang, G Wang, DA Huang, O Bastani… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have excelled as high-level semantic planners for
sequential decision-making tasks. However, harnessing them to learn complex low-level …

The unsurprising effectiveness of pre-trained vision models for control

S Parisi, A Rajeswaran… - … on machine learning, 2022 - proceedings.mlr.press
Recent years have seen the emergence of pre-trained representations as a powerful
abstraction for AI applications in computer vision, natural language, and speech. However …

Implicit behavioral cloning

P Florence, C Lynch, A Zeng… - … on Robot Learning, 2022 - proceedings.mlr.press
We find that across a wide range of robot policy learning scenarios, treating supervised
policy learning with an implicit model generally performs better, on average, than commonly …

Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

A Rame, G Couairon, C Dancette… - Advances in …, 2024 - proceedings.neurips.cc
Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned
on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further …

Amp: Adversarial motion priors for stylized physics-based character control

XB Peng, Z Ma, P Abbeel, S Levine… - ACM Transactions on …, 2021 - dl.acm.org
Synthesizing graceful and life-like behaviors for physically simulated characters has been a
fundamental challenge in computer animation. Data-driven methods that leverage motion …

A review of reinforcement learning based energy management systems for electrified powertrains: Progress, challenge, and potential solution

AH Ganesh, B Xu - Renewable and Sustainable Energy Reviews, 2022 - Elsevier
The impact of internal combustion engine-powered automobiles on climate change due to
emissions and the depletion of fossil fuels has contributed to the progress of electrified …