{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:51:06Z","timestamp":1771516266695,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"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":[[2023,8,21]]},"DOI":"10.1109\/cog57401.2023.10333194","type":"proceedings-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T18:48:21Z","timestamp":1701715701000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Gillberg","sequence":"first","affiliation":[{"name":"Electronic Arts (EA)"}]},{"given":"Joakim","family":"Bergdahl","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Alessandro","family":"Sestini","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]},{"given":"Andrew","family":"Eakins","sequence":"additional","affiliation":[{"name":"Electronic Arts (EA)"}]},{"given":"Linus","family":"Gissl\u00e9n","sequence":"additional","affiliation":[{"name":"SEED - Electronic Arts (EA)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231552"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619048"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3226910"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref5","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref6","volume-title":"Reinforcement Learning, second edition: An Introduction","author":"Sutton","year":"2018"},{"key":"ref7","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref8","article-title":"Onnx: Open neural network exchange","author":"Bai","year":"2019"},{"key":"ref9","article-title":"Onnx runtime","year":"2021"},{"key":"ref10","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3410404.3414249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2018.2808198"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848091"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MODELS.2015.7338274"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SBGAMES.2018.00015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3290607.3313039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2013.6693143"},{"key":"ref18","article-title":"Online game testing using scenario-based control of massive virtual users","volume-title":"IEEE International Conference on Advanced Communication Technology","author":"Cho"},{"key":"ref19","article-title":"Software testing by active learning for commercial games","volume-title":"Conference on Artificial Intelligence","author":"Xiao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848057"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/294"},{"key":"ref23","first-page":"2644","article-title":"Navigation turing test (ntt): Learning to evaluate human-like navigation","volume-title":"International Conference on Machine Learning","author":"Devlin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00077"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231915"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490398"},{"key":"ref27","article-title":"Reinforcement learning agents for ubisoft\u2019s roller champions","author":"Iskander","year":"2020"},{"key":"ref28","article-title":"Honor of kings arena: an environment for generalization in competitive reinforcement learning","author":"Wei","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"}],"event":{"name":"2023 IEEE Conference on Games (CoG)","location":"Boston, MA, USA","start":{"date-parts":[[2023,8,21]]},"end":{"date-parts":[[2023,8,24]]}},"container-title":["2023 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10333091\/10333129\/10333194.pdf?arnumber=10333194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:07:46Z","timestamp":1703030866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10333194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cog57401.2023.10333194","relation":{},"subject":[],"published":{"date-parts":[[2023,8,21]]}}}