paper-with-me

홈 › Papers

Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models

2024-05-07 · Ziqi Zhou, Jingyue Zhang, Jingyuan Zhang, Yangfan He, Boyue Wang, Tianyu Shi, Alaa Khamis

One of the key challenges in current Reinforcement Learning (RL)-based Automated Driving (AD) agents is achieving flexible, precise, and human-like behavior cost-effectively. This paper introduces an innovative approach that uses large language models (LLMs) to intuitively and effectively optimize RL reward functions in a human-centric way. We developed a framework where instructions and dynamic environment descriptions are input into the LLM. The LLM then utilizes this information to assist in generating rewards, thereby steering the behavior of RL agents towards patterns that more closely resemble human driving. The experimental results demonstrate that this approach not only makes RL agents more anthropomorphic but also achieves better performance. Additionally, various strategies for reward-proxy and reward-shaping are investigated, revealing the significant impact of prompt design on shaping an AD vehicle's behavior. These findings offer a promising direction for the development of more advanced, human-like automated driving systems. Our experimental data and source code can be found here

📄 PDF Abstract BibTeX arXiv:2405.04135

Code (1)

jingyue2000/in-context_learning_for_automated_driving 공식 구현

Tasks

In-Context LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

2026-02-16 · Elias Malomgré, Pieter Simoens arxiv

AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, dif…

Reinforcement Learning

EgoVLM: Policy Optimization for Egocentric Video Understanding

2025-06-03 · Ashwin Vinod, Shrey Pandit, Aditya Vavre, Linshen Liu

Emerging embodied AI applications, such as wearable cameras and autonomous agents, have underscored the need for robust reasoning from first person video streams. We introduce EgoVLM, a vision-language model specifically…

EgoSchemaQuestion Answeringreinforcement-learningReinforcement Learning+2

HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare

2023-02-18 · Ge Gao, Song Ju, Markel Sanz Ausin, Min Chi

Reinforcement learning (RL) has been extensively researched for enhancing human-environment interactions in various human-centric tasks, including e-learning and healthcare. Since deploying and evaluating policies online…

Off-policy evaluationReinforcement Learning (RL)

Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

2024-01-29 · Banghua Zhu, Michael I. Jordan, Jiantao Jiao

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique that aligns language models closely with human-centric values. The initial phase of RLHF involves learning human values using a reward model from r…

Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task

2022-03-11 · Vittorio Giammarino, Matthew F Dunne, Kylie N Moore, Michael E Hasselmo 외

We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the hi…

Deep Reinforcement LearningImitation LearningReinforcement Learning (RL)