paper-with-me

홈 › Papers

Hierarchical Potential-based Reward Shaping from Task Specifications

2021-10-06 · Luigi Berducci, Edgar A. Aguilar, Dejan Ničković, Radu Grosu

The automatic synthesis of policies for robotic-control tasks through reinforcement learning relies on a reward signal that simultaneously captures many possibly conflicting requirements. In this paper, we in\-tro\-duce a novel, hierarchical, potential-based reward-shaping approach (HPRS) for defining effective, multivariate rewards for a large family of such control tasks. We formalize a task as a partially-ordered set of safety, target, and comfort requirements, and define an automated methodology to enforce a natural order among requirements and shape the associated reward. Building upon potential-based reward shaping, we show that HPRS preserves policy optimality. Our experimental evaluation demonstrates HPRS's superior ability in capturing the intended behavior, resulting in task-satisfying policies with improved comfort, and converging to optimal behavior faster than other state-of-the-art approaches. We demonstrate the practical usability of HPRS on several robotics applications and the smooth sim2real transition on two autonomous-driving scenarios for F1TENTH race cars.

📄 PDF Abstract BibTeX arXiv:2110.02792

Code (1)

EdAlexAguilar/reward_shaping 공식 구현

Tasks

Autonomous DrivingReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications

2026-02-20 · Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar arxiv

When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behav…

Reinforcement Learning

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

2022-10-18 · Abhishek Gupta, Aldo Pacchiano, Yuexiang Zhai, Sham M. Kakade 외

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping

2022-03-08 · Ningyuan Zhang, Wenliang Liu, Calin Belta

We present a computational framework for synthesis of distributed control strategies for a heterogeneous team of robots in a partially observable environment. The goal is to cooperatively satisfy specifications given as …

reinforcement-learningReinforcement Learning (RL)

Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs

2026-05-07 · Nicholas Potteiger, Ankita Samaddar, Taylor T. Johnson, Xenofon Koutsoukos arxiv

Decomposing complex tasks into a sequence of simpler subtasks can improve learning efficiency for an autonomous agent. Reinforcement learning (RL) can be used to optimize agent policies to complete subtasks, but requires…

Reinforcement Learning

STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order

2026-01-13 · Chengyang Gu, Yuxin Pan, Hui Xiong, Yize Chen arxiv

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing go…

Reinforcement LearningOffline RL