ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving

2025-05-30 · Yongming Chen, Miner Chen, Liewen Liao, Mingyang Jiang, Xiang Zuo, Hengrui Zhang, Yuchen Xi, Songan Zhang

Reinforcement learning (RL) in autonomous driving employs a trial-and-error mechanism, enhancing robustness in unpredictable environments. However, crafting effective reward functions remains challenging, as conventional approaches rely heavily on manual design and demonstrate limited efficacy in complex scenarios. To address this issue, this study introduces a responsibility-oriented reward function that explicitly incorporates traffic regulations into the RL framework. Specifically, we introduced a Traffic Regulation Knowledge Graph and leveraged Vision-Language Models alongside Retrieval-Augmented Generation techniques to automate reward assignment. This integration guides agents to adhere strictly to traffic laws, thus minimizing rule violations and optimizing decision-making performance in diverse driving conditions. Experimental validations demonstrate that the proposed methodology significantly improves the accuracy of assigning accident responsibilities and effectively reduces the agent's liability in traffic incidents.

📄 PDF Abstract BibTeX arXiv:2505.24317

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving Decision Making Reinforcement Learning (RL)Retrieval-augmented Generation

Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning

2022-11-25 · Matthias Kraus, Nicolas Wagner, Ron Riekenbrauck, Wolfgang Minker

The next step for intelligent dialog agents is to escape their role as silent bystanders and become proactive. Well-defined proactive behavior may improve human-machine cooperation, as the agent takes a more active role …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Environmental-Impact Based Multi-Agent Reinforcement Learning

2023-11-06 · Farinaz Alamiyan-Harandi, Pouria Ramazi

To promote cooperation and strengthen the individual impact on the collective outcome in social dilemmas, we propose the Environmental-impact Multi-Agent Reinforcement Learning (EMuReL) method where each agent estimates …

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog

2019-08-28 · IJCNLP 2019 11 · Ryuichi Takanobu, Hanlin Zhu, Minlie Huang

Dialog policy decides what and how a task-oriented dialog system will respond, and plays a vital role in delivering effective conversations. Many studies apply Reinforcement Learning to learn a dialog policy with the rew…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

2026-05-19 · Minxuan Lv, Tiehua Mei, Tanlong Du, Junmin Chen 외 arxiv

We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL methods often treat data construction as…

Reinforcement Learning

From internal models toward metacognitive AI

2021-09-27 · Mitsuo Kawato, Aurelio Cortese

In several papers published in Biological Cybernetics in the 1980s and 1990s, Kawato and colleagues proposed computational models explaining how internal models are acquired in the cerebellum. These models were later sup…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)