Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915026158223360 |
|---|---|
| author | Cao, Yuji Zhao, Huan Cheng, Yuheng Shu, Ting Chen, Yue Liu, Guolong Liang, Gaoqi Zhao, Junhua Yan, Jinyue Li, Yun |
| author_facet | Cao, Yuji Zhao, Huan Cheng, Yuheng Shu, Ting Chen, Yue Liu, Guolong Liang, Gaoqi Zhao, Junhua Yan, Jinyue Li, Yun |
| contents | With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs' functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated, and provide insights into future directions. Lastly, a comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications such as robotics, autonomous driving, and energy systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00282 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods Cao, Yuji Zhao, Huan Cheng, Yuheng Shu, Ting Chen, Yue Liu, Guolong Liang, Gaoqi Zhao, Junhua Yan, Jinyue Li, Yun Machine Learning Artificial Intelligence Computation and Language Robotics With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs' functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated, and provide insights into future directions. Lastly, a comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications such as robotics, autonomous driving, and energy systems. |
| title | Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods |
| topic | Machine Learning Artificial Intelligence Computation and Language Robotics |
| url | https://arxiv.org/abs/2404.00282 |