{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:00:35Z","timestamp":1777705235913,"version":"3.51.4"},"reference-count":12,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,1,30]]},"abstract":"<jats:p>Reward signal reinforcement learning algorithms can be used to solve sequential learning problems. However, in practice, they still suffer from the problem of reward imbalance, which limits their use in many contexts. To solve this unbalanced reward problem, in this paper, we propose a novel model-based reinforcement learning algorithm called the expected n-step value iteration (EnVI). Unlike traditional model-based reinforcement learning algorithms, the proposed method uses a new return function that changes the discount of future rewards while reducing the influence of the current reward. We evaluated the performance of the proposed algorithm on a Treasure-Hunting game and a Hill-Walking game. The results demonstrate that the proposed algorithm can reduce the negative impact of unbalanced rewards and greatly improve the performance of traditional reinforcement learning algorithms.<\/jats:p>","DOI":"10.3233\/jifs-210956","type":"journal-article","created":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T11:41:10Z","timestamp":1656070870000},"page":"3233-3243","source":"Crossref","is-referenced-by-count":1,"title":["A novel model-based reinforcement learning algorithm for solving the problem of unbalanced reward"],"prefix":"10.1177","volume":"44","author":[{"given":"Yinlong","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hua","sequence":"additional","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohu","family":"Sang","sequence":"additional","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of College of Electrical Engineering, Nantong University, Nantong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of College of Automation Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-210956_ref1","unstructured":"Sutton R. and Barto A. , Introduction to rinforcement learning, MIT Press, 2017."},{"key":"10.3233\/JIFS-210956_ref2","first-page":"1","article-title":"A hierarchical self-attentiveneural extractive summarizer via reinforcement learning","volume":"2","author":"Mohsen","year":"2020","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-210956_ref3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3233\/JIFS-191567","article-title":"Bench calibration method forautomotive electric motors based on deep reinforcement learning,1\u2013","volume":"39","author":"Zhou","year":"2020","journal-title":"Journal of Intelligent and Fuzzy Systems"},{"key":"10.3233\/JIFS-210956_ref6","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"10.3233\/JIFS-210956_ref7","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Networks"},{"key":"10.3233\/JIFS-210956_ref8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neunet.2020.12.001","article-title":"Modular deep reinforcementlearning from reward and punishment for robot navigation","volume":"135","author":"Wang","year":"2020","journal-title":"Neural Networks"},{"key":"10.3233\/JIFS-210956_ref9","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"10.3233\/JIFS-210956_ref10","doi-asserted-by":"crossref","first-page":"1851","DOI":"10.1109\/TVT.2021.3055065","article-title":"An adaptiveasynchronous wake-up scheme for underwater acoustic sensor networksusing deep reinforcement learning","volume":"70","author":"Li","year":"2021","journal-title":"IEEE Transactions onVehicular Technology"},{"key":"10.3233\/JIFS-210956_ref11","first-page":"1038","article-title":"Generalization in reinforcement learning: successfulexamples using sparse coarse coding","author":"Sutton","year":"1996","journal-title":"Annual Conference onNeural Information Processing Systems, Curran Associates"},{"key":"10.3233\/JIFS-210956_ref15","doi-asserted-by":"crossref","first-page":"2874","DOI":"10.1007\/s10489-019-01417-4","article-title":"A novel multi-stepreinforcement learning method for solving reward hacking","volume":"49","author":"Yuan","year":"2019","journal-title":"Applied Intelligence"},{"key":"10.3233\/JIFS-210956_ref19","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1109\/TIT.2008.2009797","article-title":"Markov random processes are neither bandlimited norrecoverable from samples or after quantization","volume":"55","author":"Marco","year":"2009","journal-title":"IEEETransactions on Information Theory"},{"key":"10.3233\/JIFS-210956_ref21","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-210956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:43:17Z","timestamp":1777455797000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-210956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,30]]},"references-count":12,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/jifs-210956","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,30]]}}}