{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:14Z","timestamp":1755800234168,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"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":[[2025,8,26]]},"DOI":"10.1109\/cog64752.2025.11114257","type":"proceedings-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:06:42Z","timestamp":1755626802000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["RL- and LLM-Based AI Solvers for the Game of Wordle\/Fibble"],"prefix":"10.1109","author":[{"given":"Krerkkiat","family":"Chusap","sequence":"first","affiliation":[{"name":"School of EECS, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colin","family":"Murphy","sequence":"additional","affiliation":[{"name":"School of EECS, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Clay","family":"Hess","sequence":"additional","affiliation":[{"name":"School of EECS, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai Deepa","family":"Kadaru","sequence":"additional","affiliation":[{"name":"School of EECS, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Buccapatnam","sequence":"additional","affiliation":[{"name":"School of EECS, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Ohio University,Athens,Ohio,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref3","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref7","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"volume-title":"The game of Wordle.","key":"ref10"},{"volume-title":"The game of Fibble.","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref13","first-page":"21 024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"volume-title":"LLMs may not be human-level players, but they can be testers: Measuring game difficulty with 1lm agents","year":"2024","author":"Xiao","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3657604.3664671"},{"key":"ref17","article-title":"A survey on large language model-based game agents","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"On the utility of learning about humans for human-ai coordination","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Carroll","year":"2019"},{"article-title":"Implementing a wordle solver with reinforcement learning","volume-title":"Voorhs","year":"2023","key":"ref19"},{"issue":"268","key":"ref20","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024","journal-title":"arXiv preprint"},{"volume-title":"Leveraging word guessing games to assess the intelligence of large language models","year":"2023","author":"Liang","key":"ref22"}],"event":{"name":"2025 IEEE Conference on Games (CoG)","start":{"date-parts":[[2025,8,26]]},"location":"Lisbon, Portugal","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11113832\/11113841\/11114257.pdf?arnumber=11114257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T06:48:45Z","timestamp":1755672525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cog64752.2025.11114257","relation":{},"subject":[],"published":{"date-parts":[[2025,8,26]]}}}