International Journal of Control, Automation, and Systems 2025; 23(2): 449-458
https://doi.org/10.1007/s12555-024-0528-6
© The International Journal of Control, Automation, and Systems
In robotics, reinforcement learning (RL) is often used to help robots learn complex tasks through interactions with their environment. A crucial aspect of RL is the design of reward functions; these functions guide the learning process by providing feedback on a robot’s actions. However, crafting these reward functions manually is time-consuming and requires extensive human expertise. In this paper, we propose a tree of action-reward generation (TARG) model that automates reward generation for a given task without the need for human fine-tuning. By using a large language model (LLM), we create a systematic action plan sequence to generate a tree of action that guides RL training. Proposed method facilitates the automatic generation of a reward tree, which stabilizes the training process. To demonstrate the effectiveness of the proposed TARG framework, we conducted experiments involving a cabinet opening task within the IsaacSim simulation environment. The results demonstrated the potential of the proposed framework to significantly improve the adaptability and performance of robots in complex settings.
Keywords Large language model, reinforcement learning, reward generation, robot manipulation, task planning.
International Journal of Control, Automation, and Systems 2025; 23(2): 449-458
Published online February 1, 2025 https://doi.org/10.1007/s12555-024-0528-6
Copyright © The International Journal of Control, Automation, and Systems.
Sung-Gil Park, Han-Byeol Kim, Yong-Jun Lee, Woo-Jin Ahn*, and Myo Taeg Lim*
Korea University
In robotics, reinforcement learning (RL) is often used to help robots learn complex tasks through interactions with their environment. A crucial aspect of RL is the design of reward functions; these functions guide the learning process by providing feedback on a robot’s actions. However, crafting these reward functions manually is time-consuming and requires extensive human expertise. In this paper, we propose a tree of action-reward generation (TARG) model that automates reward generation for a given task without the need for human fine-tuning. By using a large language model (LLM), we create a systematic action plan sequence to generate a tree of action that guides RL training. Proposed method facilitates the automatic generation of a reward tree, which stabilizes the training process. To demonstrate the effectiveness of the proposed TARG framework, we conducted experiments involving a cabinet opening task within the IsaacSim simulation environment. The results demonstrated the potential of the proposed framework to significantly improve the adaptability and performance of robots in complex settings.
Keywords: Large language model, reinforcement learning, reward generation, robot manipulation, task planning.
Vol. 23, No. 2, pp. 359~682
Tiantian Hao*, De Xu, and Shaohua Yan
International Journal of Control, Automation, and Systems 2024; 22(5): 1613-1623Subin Lim and Sangrok Jin*
International Journal of Control, Automation, and Systems 2023; 21(11): 3540-3550Haipeng Chen, Wenxing Fu, Junmin Liu, Dengxiu Yu, and Kang Chen*
International Journal of Control, Automation, and Systems 2023; 21(10): 3443-3455