{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:15:25Z","timestamp":1740147325228,"version":"3.37.3"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,6,3]],"date-time":"2023-06-03T00:00:00Z","timestamp":1685750400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,3]],"date-time":"2023-06-03T00:00:00Z","timestamp":1685750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SOCA"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s11761-023-00365-9","type":"journal-article","created":{"date-parts":[[2023,6,3]],"date-time":"2023-06-03T18:01:25Z","timestamp":1685815285000},"page":"303-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Critical path-driven exploration on the MiniGrid environment"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3973-9334","authenticated-orcid":false,"given":"Yan","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,3]]},"reference":[{"key":"365_CR1","unstructured":"Bellemare M, Srinivasan S, Ostrovski G, Schaul T, Saxton D, Munos R (2016) Unifying count-based exploration and intrinsic motivation. Adv Neural Inform Process Syst. 29"},{"key":"365_CR2","unstructured":"Ecoffet A, Huizinga J, Lehman J, Stanley KO, Clune J (2019) Go-explore: a new approach for hard-exploration problems. arXiv preprint arXiv:1901.10995"},{"key":"365_CR3","doi-asserted-by":"crossref","unstructured":"Pathak D, Agrawal P, Efros AA, Darrell T (2017) Curiosity-driven exploration by self-supervised prediction. In: International conference on machine learning, pp 2778\u20132787. PMLR","DOI":"10.1109\/CVPRW.2017.70"},{"key":"365_CR4","unstructured":"Burda Y, Edwards H, Pathak D, Storkey A, Darrell T, Efros AA (2018) Large-scale study of curiosity-driven learning. arXiv preprint arXiv:1808.04355"},{"key":"365_CR5","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp 1928\u20131937. PMLR"},{"key":"365_CR6","unstructured":"Bai C, Liu P, Liu K, Wang L, Zhao Y, Han L, Wang Z (2021) Variational dynamic for self-supervised exploration in deep reinforcement learning. IEEE Transactions on neural networks and learning systems"},{"key":"365_CR7","unstructured":"Rajeswaran A, Lowrey K, Todorov EV, Kakade SM (2017) Towards generalization and simplicity in continuous control. Adv Neural Inform Process Syst. 30"},{"key":"365_CR8","unstructured":"Zhang C, Vinyals O, Munos R, Bengio S (2018) A study on overfitting in deep reinforcement learning. arXiv preprint arXiv:1804.06893"},{"key":"365_CR9","unstructured":"Cobbe K, Klimov O, Hesse C, Kim T, Schulman J (2019) Quantifying generalization in reinforcement learning. In: International conference on machine learning, pp 1282\u20131289. PMLR"},{"key":"365_CR10","doi-asserted-by":"crossref","unstructured":"Juliani A, Khalifa A, Berges V-P, Harper J, Teng E, Henry H, Crespi A, Togelius J, Lange D (2019) Obstacle tower: A generalization challenge in vision, control, and planning. arXiv preprint arXiv:1902.01378","DOI":"10.24963\/ijcai.2019\/373"},{"key":"365_CR11","unstructured":"Raileanu R, Rockt\u00e4schel T (2020) Ride: Rewarding impact-driven exploration for procedurally-generated environments. arXiv preprint arXiv:2002.12292"},{"key":"365_CR12","unstructured":"Burda Y, Edwards H, Storkey A, Klimov O (2018) Exploration by random network distillation. arXiv preprint arXiv:1810.12894"},{"key":"365_CR13","unstructured":"Kim H, Kim J, Jeong Y, Levine S, Song HO (2018) Emi: Exploration with mutual information. arXiv preprint arXiv:1810.01176"},{"key":"365_CR14","unstructured":"Song Y, Chen Y, Hu Y, Fan C (2020) Exploring unknown states with action balance. arXiv preprint arXiv:2003.04518"},{"key":"365_CR15","unstructured":"Kim Y, Nam W, Kim H, Kim JH, Kim G (2019) Curiosity-bottleneck: Exploration by distilling task-specific novelty. In: International conference on machine learning, pp 3379\u20133388. PMLR"},{"key":"365_CR16","unstructured":"Ostrovski G, Bellemare MG, Oord A, Munos R (2017) Count-based exploration with neural density models. In: International conference on machine learning, pp 2721\u20132730. PMLR"},{"key":"365_CR17","first-page":"8114","volume":"33","author":"RY Tao","year":"2020","unstructured":"Tao RY, Fran\u00e7ois-Lavet V, Pineau J (2020) Novelty search in representational space for sample efficient exploration. Adv Neural Inform Process Syst 33:8114\u20138126","journal-title":"Adv Neural Inform Process Syst"},{"key":"365_CR18","doi-asserted-by":"crossref","unstructured":"Kang Y, Zhao E, Li K, Xing J (2021) Exploration via state influence modeling. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 8047\u20138054","DOI":"10.1609\/aaai.v35i9.16981"},{"key":"365_CR19","unstructured":"Chevalier-Boisvert M, Willems L, Pal S (2018) Minimalistic gridworld environment for openai gym"},{"key":"365_CR20","unstructured":"Espeholt L, Soyer H, Munos R, Simonyan K, Mnih V, Ward T, Doron Y, Firoiu V, Harley T, Dunning I, et al. (2018) Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures. In: International conference on machine learning, pp 1407\u20131416. PMLR"}],"container-title":["Service Oriented Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11761-023-00365-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11761-023-00365-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11761-023-00365-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T07:48:03Z","timestamp":1697528883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11761-023-00365-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,3]]},"references-count":20,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["365"],"URL":"https:\/\/doi.org\/10.1007\/s11761-023-00365-9","relation":{},"ISSN":["1863-2386","1863-2394"],"issn-type":[{"type":"print","value":"1863-2386"},{"type":"electronic","value":"1863-2394"}],"subject":[],"published":{"date-parts":[[2023,6,3]]},"assertion":[{"value":"28 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest\/competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}