{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T08:56:50Z","timestamp":1742979410051,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031553257"},{"type":"electronic","value":"9783031553264"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-55326-4_11","type":"book-chapter","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:46:10Z","timestamp":1710405970000},"page":"223-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Study on LSTM and ConvLSTM Memory-Based Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9503-9084","authenticated-orcid":false,"given":"Fernando Fradique","family":"Duarte","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0513-158X","authenticated-orcid":false,"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7099-1247","authenticated-orcid":false,"given":"Artur","family":"Pereira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4709-1718","authenticated-orcid":false,"given":"Lu\u00eds Paulo","family":"Reis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,15]]},"reference":[{"key":"11_CR1","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs. In: AAAI Fall Symposium - Technical Report, AI Access Foundation, pp. 29\u201337 (2015)"},{"key":"11_CR2","unstructured":"Heess, N., Hunt, J.J., Lillicrap, T.P., Silver, D.: Memory-based control with recurrent neural networks. arXiv:1512.04455, Preprint (2015)"},{"key":"11_CR3","unstructured":"Sorokin, I., Seleznev, A., Pavlov, M., Fedorov, A., Ignateva, A.: Deep attention recurrent Q-network. http:\/\/arxiv.org\/abs\/1512.01693, Preprint (2015)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Tang, Y., Nguyen, D., Ha, D.: Neuroevolution of self-interpretable agents. In: GECCO 2020: Genetic and Evolutionary Computation Conference, pp. 414\u2013424. ACM, Canc\u00fan Mexico (2020)","DOI":"10.1145\/3377930.3389847"},{"key":"11_CR5","unstructured":"Mott, A., Zoran, D., Chrzanowski, M., Wierstra, D., Rezende, D.J.: Towards interpretable reinforcement learning using attention augmented agents. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, pp. 12329\u201312338 (2019)"},{"key":"11_CR6","unstructured":"Ha, D., Schmidhuber, J.: World models. http:\/\/arxiv.org\/abs\/1803.10122, Preprint (2018)"},{"key":"11_CR7","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. In: Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, Montr\u00e9al, Canada, pp. 2455\u20132467 (2018)"},{"issue":"8","key":"11_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"11_CR9","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, Montreal, Quebec, Canada, pp. 802\u2013810 (2015)"},{"key":"11_CR10","unstructured":"Bishop, C.M.: Mixture Density Networks (1994)"},{"key":"11_CR11","unstructured":"Kalchbrenner, N., Danihelka, I., Graves, A.: Grid long short-term memory. In: 4th International Conference on Learning Representations, ICLR (2016)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Duarte, F.F., Lau, N., Pereira, A., Reis, L.P.: LSTM, ConvLSTM, MDN-RNN and GridLSTM memory-based deep reinforcement learning. In: Proceedings of the 15th International Conference on Agents and Artificial Intelligence, ICAART 2023, Lisbon, Portugal, pp. 169\u2013179. SCITEPRESS (2023)","DOI":"10.5220\/0011664900003393"},{"key":"11_CR13","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, pp. 1787\u20131796. PMLR (2018)"},{"key":"11_CR14","unstructured":"Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. http:\/\/arxiv.org\/abs\/1410.5401, Preprint (2014)"},{"issue":"7626","key":"11_CR15","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471\u2013476 (2016)","journal-title":"Nature"},{"issue":"1\u20132","key":"11_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"issue":"7540","key":"11_CR17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"11_CR18","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. http:\/\/arxiv.org\/abs\/1308.0850, Preprint (2013)"},{"key":"11_CR19","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, Quebec, Canada, pp. 3104\u20133112 (2014)"},{"key":"11_CR20","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, pp. 843\u2013852. JMLR (2015)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, pp. 551\u2013561. The Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/D16-1053"},{"key":"11_CR22","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, pp. 8024\u20138035 (2019)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.E.: Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"11_CR24","unstructured":"Ba, L.J., Kiros, J.R., Hinton, G.E.: Layer normalization. https:\/\/arxiv.org\/abs\/1607.06450, Preprint (2016)"},{"key":"11_CR25","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, pp. 448\u2013456. JMLR (2015)"},{"key":"11_CR26","first-page":"523","volume":"61","author":"MC Machado","year":"2018","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M.J., Bowling, M.: Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. Artif. Intell. 61, 523\u2013562 (2018)","journal-title":"Artif. Intell."},{"key":"11_CR27","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, pp. 1928\u20131937. JMLR (2016)"},{"key":"11_CR28","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA (2015)"},{"key":"11_CR29","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M.I., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico (2016)"},{"key":"11_CR30","unstructured":"Brockman, G., et al.: OpenAI Gym. CoRR (2016)"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-55326-4_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:47:50Z","timestamp":1710406070000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-55326-4_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031553257","9783031553264"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-55326-4_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 February 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 February 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaart.scitevents.org\/?y=2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"306","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":"23","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":"111","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":"8% - 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":"3","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":"4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}