Evolutionary Reinforcement Learning: A Systematic Review and Future Directions
In response to the limitations of reinforcement learning and Evolutionary Algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. This systematic review aims to provide a comprehensive analysis of EvoRL, examining the symbiotic...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/5/833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850051809644642304 |
|---|---|
| author | Yuanguo Lin Fan Lin Guorong Cai Hong Chen Linxin Zou Yunxuan Liu Pengcheng Wu |
| author_facet | Yuanguo Lin Fan Lin Guorong Cai Hong Chen Linxin Zou Yunxuan Liu Pengcheng Wu |
| author_sort | Yuanguo Lin |
| collection | DOAJ |
| description | In response to the limitations of reinforcement learning and Evolutionary Algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. This systematic review aims to provide a comprehensive analysis of EvoRL, examining the symbiotic relationship between EAs and reinforcement learning algorithms and identifying critical gaps in relevant application tasks. The review begins by outlining the technological foundations of EvoRL, detailing the complementary relationship between EAs and reinforcement learning algorithms to address the limitations of reinforcement learning, such as parameter sensitivity, sparse rewards, and its susceptibility to local optima. We then delve into the challenges faced by both reinforcement learning and EvoRL, exploring the utility and limitations of EAs in EvoRL. EvoRL itself is constrained by the sampling efficiency and algorithmic complexity, which affect its application in areas like robotic control and large-scale industrial settings. Furthermore, we address significant open issues in the field, such as adversarial robustness, fairness, and ethical considerations. Finally, we propose future directions for EvoRL, emphasizing research avenues that strive to enhance self-adaptation, self-improvement, scalability, interpretability, and so on. To quantify the current state, we analyzed about 100 EvoRL studies, categorizing them based on algorithms, performance metrics, and benchmark tasks. Serving as a comprehensive resource for researchers and practitioners, this systematic review provides insights into the current state of EvoRL and offers a guide for advancing its capabilities in the ever-evolving landscape of artificial intelligence. |
| format | Article |
| id | doaj-art-668f030e2a6b4de7b3c5448c0bf36f3b |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-668f030e2a6b4de7b3c5448c0bf36f3b2025-08-20T02:53:02ZengMDPI AGMathematics2227-73902025-03-0113583310.3390/math13050833Evolutionary Reinforcement Learning: A Systematic Review and Future DirectionsYuanguo Lin0Fan Lin1Guorong Cai2Hong Chen3Linxin Zou4Yunxuan Liu5Pengcheng Wu6School of Computer Engineering, Jimei University, Xiamen 361021, ChinaSchool of Informatics, Xiamen University, Xiamen 361005, ChinaSchool of Computer Engineering, Jimei University, Xiamen 361021, ChinaInformation Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, ChinaSchool of Cyber Science and Engineering, Wuhan University, Wuhan 430074, ChinaSchool of Computer Engineering, Jimei University, Xiamen 361021, ChinaWebank-NTU Joint Research Institute on Fintech, Nanyang Technological University, Singapore 639798, SingaporeIn response to the limitations of reinforcement learning and Evolutionary Algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. This systematic review aims to provide a comprehensive analysis of EvoRL, examining the symbiotic relationship between EAs and reinforcement learning algorithms and identifying critical gaps in relevant application tasks. The review begins by outlining the technological foundations of EvoRL, detailing the complementary relationship between EAs and reinforcement learning algorithms to address the limitations of reinforcement learning, such as parameter sensitivity, sparse rewards, and its susceptibility to local optima. We then delve into the challenges faced by both reinforcement learning and EvoRL, exploring the utility and limitations of EAs in EvoRL. EvoRL itself is constrained by the sampling efficiency and algorithmic complexity, which affect its application in areas like robotic control and large-scale industrial settings. Furthermore, we address significant open issues in the field, such as adversarial robustness, fairness, and ethical considerations. Finally, we propose future directions for EvoRL, emphasizing research avenues that strive to enhance self-adaptation, self-improvement, scalability, interpretability, and so on. To quantify the current state, we analyzed about 100 EvoRL studies, categorizing them based on algorithms, performance metrics, and benchmark tasks. Serving as a comprehensive resource for researchers and practitioners, this systematic review provides insights into the current state of EvoRL and offers a guide for advancing its capabilities in the ever-evolving landscape of artificial intelligence.https://www.mdpi.com/2227-7390/13/5/833evolutionary reinforcement learningevolutionary algorithmsdeep learningpolicy searchevolution strategy |
| spellingShingle | Yuanguo Lin Fan Lin Guorong Cai Hong Chen Linxin Zou Yunxuan Liu Pengcheng Wu Evolutionary Reinforcement Learning: A Systematic Review and Future Directions Mathematics evolutionary reinforcement learning evolutionary algorithms deep learning policy search evolution strategy |
| title | Evolutionary Reinforcement Learning: A Systematic Review and Future Directions |
| title_full | Evolutionary Reinforcement Learning: A Systematic Review and Future Directions |
| title_fullStr | Evolutionary Reinforcement Learning: A Systematic Review and Future Directions |
| title_full_unstemmed | Evolutionary Reinforcement Learning: A Systematic Review and Future Directions |
| title_short | Evolutionary Reinforcement Learning: A Systematic Review and Future Directions |
| title_sort | evolutionary reinforcement learning a systematic review and future directions |
| topic | evolutionary reinforcement learning evolutionary algorithms deep learning policy search evolution strategy |
| url | https://www.mdpi.com/2227-7390/13/5/833 |
| work_keys_str_mv | AT yuanguolin evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT fanlin evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT guorongcai evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT hongchen evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT linxinzou evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT yunxuanliu evolutionaryreinforcementlearningasystematicreviewandfuturedirections AT pengchengwu evolutionaryreinforcementlearningasystematicreviewandfuturedirections |