相关论文: Learning Personalized Driving Styles via Reinforce…

In the realm of autonomous vehicles, dynamic user preferences are critical yet challenging to accommodate. Existing methods often misrepresent these preferences, either by overlooking their dynamism or overburdening users as humans often…

Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this…

Designing effective reward functions is crucial to training reinforcement learning (RL) algorithms. However, this design is non-trivial, even for domain experts, due to the subjective nature of certain tasks that are hard to quantify…

Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned…

One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs…

Reinforcement Learning from human feedback (RLHF) has been shown a promising direction for aligning generative models with human intent and has also been explored in recent works for alignment of diffusion generative models. In this work,…

Engineering a high-performance race car requires a direct consideration of the human driver using real-world tests or Human-Driver-in-the-Loop simulations. Apart from that, offline simulations with human-like race driver models could make…

Understanding driver interactions is critical to designing autonomous vehicles to interoperate safely with human-driven cars. We consider the impact of these interactions on the policies drivers employ when navigating unsigned intersections…

We study the problem of reinforcement learning from human feedback (RLHF), a critical problem in training large language models, from a theoretical perspective. Our main contribution is the design of novel sample-efficient RLHF algorithms…

Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs),…

Training multi-modal large language models (MLLMs) that align with human intentions is a long-term challenge. Traditional score-only reward models for alignment suffer from low accuracy, weak generalization, and poor interpretability,…

Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow…

The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the training process progresses, the output distribution of the…

We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model…

This paper studies the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We first identify the primary challenges of existing popular methods like offline PPO and offline DPO as lacking in…

Success in racing requires a unique combination of vehicle setup, understanding of the racetrack, and human expertise. Since building and testing many different vehicle configurations in the real world is prohibitively expensive,…

Trajectory generation has recently drawn growing interest in privacy-preserving urban mobility studies and location-based service applications. Although many studies have used deep learning or generative AI methods to model trajectories and…

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward…

While Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning generative AI, we present empirical evidence that it can also cause severe, systematic misalignment. We hypothesize that this stems from evaluator…