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 …
Social interactions for autonomous driving: A review and perspectives
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 …
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
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 …
Subject-driven text-to-image generation via apprenticeship learning
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 …
in generating highly customized images of a target subject, by fine-tuning an``expert …
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 …
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 …
abstraction for AI applications in computer vision, natural language, and speech. However …
Implicit behavioral cloning
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 …
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
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 …
on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further …
Amp: Adversarial motion priors for stylized physics-based character control
Synthesizing graceful and life-like behaviors for physically simulated characters has been a
fundamental challenge in computer animation. Data-driven methods that leverage motion …
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 …
emissions and the depletion of fossil fuels has contributed to the progress of electrified …