{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:33:42Z","timestamp":1743006822580,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916412"},{"type":"electronic","value":"9789819916429"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-1642-9_13","type":"book-chapter","created":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:14:57Z","timestamp":1681388097000},"page":"148-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disentangling Exploration and\u00a0Exploitation in\u00a0Deep Reinforcement Learning Using Contingency Awareness"],"prefix":"10.1007","author":[{"given":"Ionel","family":"Hosu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Traian","family":"Rebedea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u0218tefan","family":"Tr\u0103u\u0219an-Matu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,14]]},"reference":[{"key":"13_CR1","unstructured":"Badia, A.P., et al.: Agent57: outperforming the atari human benchmark. ArXiv abs\/2003.13350 (2020)"},{"key":"13_CR2","unstructured":"Badia, A.P., et al.: Never give up: learning directed exploration strategies. ArXiv abs\/2002.06038 (2020)"},{"key":"13_CR3","first-page":"1471","volume":"29","author":"M Bellemare","year":"2016","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. Adv. Neural Inf. Process. Syst. 29, 1471\u20131479 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents (extended abstract). J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"13_CR5","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. ArXiv abs\/1606.01868 (2016)"},{"key":"13_CR6","unstructured":"Bellemare, M.G., Veness, J., Bowling, M.: Investigating contingency awareness using Atari 2600 games. In: Twenty-Sixth AAAI Conference on Artificial Intelligence (2012)"},{"key":"13_CR7","unstructured":"Beyer, L., Vincent, D., Teboul, O., Gelly, S., Geist, M., Pietquin, O.: Mulex: disentangling exploitation from exploration in deep rl. arXiv preprint arXiv:1907.00868 (2019)"},{"key":"13_CR8","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"13_CR9","unstructured":"Burda, Y., Edwards, H.A., Pathak, D., Storkey, A.J., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. ArXiv abs\/1808.04355 (2019)"},{"key":"13_CR10","unstructured":"Choi, J., et al.: Contingency-aware exploration in reinforcement learning. ArXiv abs\/1811.01483 (2019)"},{"key":"13_CR11","unstructured":"Houthooft, R., Chen, X., Duan, Y., Schulman, J., De Turck, F., Abbeel, P.: Vime: variational information maximizing exploration. arXiv preprint arXiv:1605.09674 (2016)"},{"key":"13_CR12","unstructured":"Kapturowski, S., Ostrovski, G., Dabney, W., Quan, J., Munos, R.: Recurrent experience replay in distributed reinforcement learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=r1lyTjAqYX"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Martin, J., Sasikumar, S.N., Everitt, T., Hutter, M.: Count-based exploration in feature space for reinforcement learning. arXiv preprint arXiv:1706.08090 (2017)","DOI":"10.24963\/ijcai.2017\/344"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Martin, J., Sasikumar, S.N., Everitt, T., Hutter, M.: Count-based exploration in feature space for reinforcement learning. In: IJCAI (2017)","DOI":"10.24963\/ijcai.2017\/344"},{"key":"13_CR15","first-page":"4026","volume":"29","author":"I Osband","year":"2016","unstructured":"Osband, I., Blundell, C., Pritzel, A., Van Roy, B.: Deep exploration via bootstrapped DQN. Adv. Neural. Inf. Process. Syst. 29, 4026\u20134034 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR16","unstructured":"Ostrovski, G., Bellemare, M.G., Oord, A., Munos, R.: Count-based exploration with neural density models. In: International Conference on Machine Learning, pp. 2721\u20132730. PMLR (2017)"},{"key":"13_CR17","unstructured":"Ostrovski, G., Bellemare, M.G., van den Oord, A., Munos, R.: Count-based exploration with neural density models. ArXiv abs\/1703.01310 (2017)"},{"key":"13_CR18","first-page":"6","volume":"1","author":"PY Oudeyer","year":"2009","unstructured":"Oudeyer, P.Y., Kaplan, F.: What is intrinsic motivation? A typology of computational approaches. Front. Neurorobot. 1, 6 (2009)","journal-title":"Front. Neurorobot."},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"13_CR20","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"13_CR21","unstructured":"Schmidhuber, J.: Adaptive confidence and adaptive curiosity. In: Institut fur Informatik, Technische Universitat Munchen, Arcisstr. 21, 800 Munchen 2. Citeseer (1991)"},{"key":"13_CR22","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"13_CR23","unstructured":"Tang, H., et al.: # exploration: a study of count-based exploration for deep reinforcement learning. In: 31st Conference on Neural Information Processing Systems (NIPS), vol. 30, pp. 1\u201318 (2017)"},{"key":"13_CR24","unstructured":"Tang, H., et al.: Exploration: a study of count-based exploration for deep reinforcement learning. In: NIPS (2017)"},{"issue":"2","key":"13_CR25","first-page":"123","volume":"12","author":"JS Watson","year":"1966","unstructured":"Watson, J.S.: The development and generalization of contingency awareness in early infancy: some hypotheses. Merrill-Palmer Q. Behav. Dev. 12(2), 123\u2013135 (1966)","journal-title":"Merrill-Palmer Q. Behav. Dev."},{"key":"13_CR26","unstructured":"Zheng, Z., Oh, J., Singh, S.: On learning intrinsic rewards for policy gradient methods. arXiv preprint arXiv:1804.06459 (2018)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1642-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T12:23:41Z","timestamp":1681388621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1642-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916412","9789819916429"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1642-9_13","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"14 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"359","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.65","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}