{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:11:58Z","timestamp":1788844318973,"version":"build-2803163510"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00073","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:10:05Z","timestamp":1788808205000},"page":"552-562","source":"Crossref","is-referenced-by-count":0,"title":["StockRL: Execution-Grounded Reinforcement Learning for AI-Driven Portfolio Decision Support with Dual-Level Reward Models"],"prefix":"10.1109","author":[{"given":"Boyang","family":"Yin","sequence":"first","affiliation":[{"name":"College of Software, Northeastern University","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Software, Northeastern University","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Software, Northeastern University","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations","author":"Yao","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3386\/w25398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3309547"},{"key":"ref4","article-title":"Can chatgpt forecast stock price movements? return predictability and large language models","author":"Lopez-Lira","year":"2023","journal-title":"CoRR abs\/2304.07619"},{"key":"ref5","article-title":"Bloomberggpt: A large language model for finance","author":"Wu","year":"2023","journal-title":"CoRR abs\/2023.17564"},{"key":"ref6","article-title":"Fingpt: Open-source financial large language models","author":"Yang","year":"2023","journal-title":"CoRR abs\/2306.06031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3737257"},{"key":"ref10","article-title":"A survey of temporal credit assignment in deep reinforcement learning","author":"Pignatelli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Icml","volume":"99","author":"Ng","year":"1999"},{"key":"ref12","article-title":"Rudder: Return decomposition for delayed rewards","volume":"32","author":"Arjona-Medina","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Chatgpt informed graph neural network for stock movement prediction","author":"Chen","year":"2023","journal-title":"CoRR abs\/2306.03763"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.185"},{"key":"ref15","article-title":"Stocktime: A time series specialized large language model architecture for stock price prediction","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.69"},{"key":"ref17","author":"Garza","year":"2023","journal-title":"Timegpt-1, CoRR abs\/2310.03589"},{"key":"ref18","article-title":"Lag-llama: Towards foundation models for time series forecasting","author":"Rasul","year":"2023","journal-title":"CoRR abs\/2310.08278"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/1911-3846.12832"},{"key":"ref20","article-title":"Marketsage: A multi-modal foundation model for market prediction","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref22","first-page":"3","article-title":"Deep reinforcement learning for portfolio management","volume-title":"Proceedings of the International Conference on Neural Information Processing","author":"Jiang","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3737257"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16144"},{"issue":"4","key":"ref25","first-page":"1379","article-title":"Market impact and optimal trading with heterogeneous market makers","volume":"30","author":"Lin","year":"2020","journal-title":"Mathematical Finance"},{"key":"ref26","article-title":"Adaptive portfolio management with deep reinforcement learning","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Fine-grained human feedback gives better rewards for language model training","volume":"36","author":"Wu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2024","journal-title":"CoRR abs\/2305.20050"},{"key":"ref29","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref30","first-page":"1","article-title":"Time-weighted return and performance attribution","volume":"21","author":"Benhamou","year":"2020","journal-title":"Journal of Asset Management"},{"key":"ref31","article-title":"Dense reward for free in reinforcement learning from human feedback","author":"Chan","year":"2024","journal-title":"CoRR abs\/2402.00782"},{"key":"ref32","article-title":"Hindsight credit assignment","volume":"32","author":"Harutyunyan","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"CoRR abs\/1707.06347"},{"key":"ref34","article-title":"Verl: An efficient and scalable library for training large language models with rl","author":"Shao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref36","article-title":"Highdimensional continuous control using generalized advantage estimation","volume-title":"4th International Conference on Learning Representations, ICLR 2016","author":"Schulman","year":"2016"},{"key":"ref37","article-title":"Q. Team, Qwen2.5: A party of foundation models","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670063.pdf?arnumber=11670063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:52:49Z","timestamp":1788843169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00073","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}