{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:40:06Z","timestamp":1745966406633,"version":"3.40.4"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030461324"},{"type":"electronic","value":"9783030461331"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_7","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"103-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stochastic Activation Actor Critic Methods"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9973-3092","authenticated-orcid":false,"given":"Wenling","family":"Shang","sequence":"first","affiliation":[]},{"given":"Douwe","family":"van der Wal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1583-3692","authenticated-orcid":false,"given":"Herke","family":"van Hoof","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1484-2121","authenticated-orcid":false,"given":"Max","family":"Welling","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"7_CR1","unstructured":"Adamski, I., Adamski, R., Grel, T., Jedrych, A., Kaczmarek, K., Michalewski, H.: Distributed deep reinforcement learning: learn how to play Atari games in 21 minutes. arXiv (2016)"},{"key":"7_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv (2016)"},{"key":"7_CR3","unstructured":"Bellemare, M., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: NIPS (2016)"},{"key":"7_CR4","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: ICML (2017)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. In: IJCAI (2013)","DOI":"10.1613\/jair.3912"},{"key":"7_CR6","unstructured":"Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D.: Weight uncertainty in neural networks. In: ICML (2015)"},{"key":"7_CR7","unstructured":"Brockman, G., et al.: OpenAI Gym (2016)"},{"key":"7_CR8","unstructured":"Chen, J., Monga, R., Bengio, S., Jozefowicz, R.: Revisiting distributed synchronous SGD. arXiv (2016)"},{"key":"7_CR9","unstructured":"Florensa, C., Duan, Y., Abbeel, P.: Stochastic neural networks for hierarchical reinforcement learning. In: ICLR (2017)"},{"key":"7_CR10","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. In: ICLR (2018)"},{"key":"7_CR11","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML (2016)"},{"key":"7_CR12","unstructured":"Gal, Y., McAllister, R., Rasmussen, C.E.: Improving PILCO with bayesian neural network dynamics models. In: ICML Workshop (2016)"},{"issue":"5\u2014-6","key":"7_CR13","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1561\/2200000049","volume":"8","author":"M Ghavamzadeh","year":"2015","unstructured":"Ghavamzadeh, M., Mannor, S., Pineau, J., Tamar, A., et al.: Bayesian reinforcement learning: a survey. Found. Trends\u00ae Mach. Learn. 8(5\u2014-6), 359\u2013483 (2015)","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"7_CR14","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290 (2018)"},{"key":"7_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"7_CR16","unstructured":"Kahn, G., Villaflor, A., Pang, V., Abbeel, P., Levine, S.: Uncertainty-aware reinforcement learning for collision avoidance. In: arxiv (2016)"},{"key":"7_CR17","unstructured":"Kingma, D.P., Salimans, T., Welling, M.: Variational dropout and the local reparameterization trick. In: NIPS (2015)"},{"key":"7_CR18","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2013)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Kuss, M., Rasmussen, C.E.: Gaussian processes in reinforcement learning. In: NIPS (2004)","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"7_CR20","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"7_CR21","unstructured":"Louizos, C., Ullrich, K., Welling, M.: Bayesian compression for deep learning. In: NIPS (2017)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M., Bowling, M.: Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. arXiv (2017)","DOI":"10.1613\/jair.5699"},{"key":"7_CR23","unstructured":"Barth-Maron, G., et al.: Distributional policy gradients. In: ICLR (2018)"},{"key":"7_CR24","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML (2016)"},{"key":"7_CR25","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"7_CR26","unstructured":"Murphy, K.P.: A survey of POMDP solution techniques. Technical Report (2000)"},{"key":"7_CR27","unstructured":"Neal, R.M.: Learning stochastic feedforward networks. Technical Report (1990)"},{"key":"7_CR28","unstructured":"O\u2019Donoghue, B., Munos, R., Kavukcuoglu, K., Mnih, V.: Combining policy gradient and q-learning. arXiv preprint arXiv:1611.01626 (2016)"},{"key":"7_CR29","unstructured":"Osband, I., Russo, D., Wen, Z., Van Roy, B.: Deep exploration via randomized value functions. arXiv (2017)"},{"key":"7_CR30","unstructured":"Osband, I., Van Roy, B., Wen, Z.: Generalization and exploration via randomized value functions. In: ICML (2016)"},{"key":"7_CR31","unstructured":"Ostrovski, G., Bellemare, M.G., Oord, A.V.D., Munos, R.: Count-based exploration with neural density models. In: ICML (2017)"},{"key":"7_CR32","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. In: ICLR (2018)"},{"key":"7_CR33","unstructured":"Prentice, S., Roy, N.: The belief roadmap: efficient planning in linear pomdps by factoring the covariance (2007)"},{"key":"7_CR34","unstructured":"Pritzel, A., et al.: Neural episodic control. In: ICML (2017)"},{"key":"7_CR35","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: ICML (2015)"},{"key":"7_CR36","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: ICLR (2016)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Shang, W., Sohn, K., Almeida, D., Lee, H.: Understanding and improving convolutional neural networks via concatenated rectified linear units. In: ICML (2016)","DOI":"10.1609\/aaai.v31i1.10759"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. Artificial Intelligence (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"7_CR39","unstructured":"Tang, Y., Salakhutdinov, R.R.: Learning stochastic feedforward neural networks. In: NIPS (2013)"},{"key":"7_CR40","unstructured":"Tian, Y., Gong, Q.: Latent forward model for real-time strategy game planning with incomplete information. In: NIPS Symposium (2017)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Todorov, E.: General duality between optimal control and estimation. In: CDC (2008)","DOI":"10.1109\/CDC.2008.4739438"},{"key":"7_CR42","unstructured":"Wang, J.X., et al.: Learning to reinforcement learn. arXiv (2016)"},{"key":"7_CR43","unstructured":"Wang, Z., et al.: Sample efficient actor-critic with experience replay. In: ICLR (2016)"},{"key":"7_CR44","unstructured":"Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: NIPS (2017)"},{"key":"7_CR45","unstructured":"Ziebart, B.D., Maas, A.L., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning (2008)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46133-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:03:46Z","timestamp":1745964226000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","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)"}}]}}