{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:14:06Z","timestamp":1743146046079,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030876258"},{"type":"electronic","value":"9783030876265"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87626-5_25","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T06:14:35Z","timestamp":1632896075000},"page":"338-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Critic Guided Segmentation of Rewarding Objects in First-Person Views"],"prefix":"10.1007","author":[{"given":"Andrew","family":"Melnik","sequence":"first","affiliation":[]},{"given":"Augustin","family":"Harter","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Limberg","sequence":"additional","affiliation":[]},{"given":"Krishan","family":"Rana","sequence":"additional","affiliation":[]},{"given":"Niko","family":"S\u00fcnderhauf","sequence":"additional","affiliation":[]},{"given":"Helge","family":"Ritter","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"25_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1007\/978-3-030-64580-9_52","volume-title":"Machine Learning, Optimization, and Data Science","author":"N Bach","year":"2020","unstructured":"Bach, N., Melnik, A., Schilling, M., Korthals, T., Ritter, H.: Learn to move through a combination of policy gradient algorithms: DDPG, D4PG, and TD3. In: Nicosia, G., et al. (eds.) LOD 2020. LNCS, vol. 12566, pp. 631\u2013644. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64580-9_52"},{"key":"25_CR2","unstructured":"Greydanus, S., Koul, A., Dodge, J., Fern, A.: Visualizing and understanding Atari agents. In: International Conference on Machine Learning, pp. 1792\u20131801. PMLR (2018)"},{"issue":"2","key":"25_CR3","first-page":"44","volume":"40","author":"D Gunning","year":"2019","unstructured":"Gunning, D., Aha, D.: Darpa\u2019s explainable artificial intelligence (XAI) program. AI Mag. 40(2), 44\u201358 (2019)","journal-title":"AI Mag."},{"key":"25_CR4","unstructured":"Guss, W.H., et al.: Towards robust and domain agnostic reinforcement learning competitions: MineRL 2020. In: NeurIPS 2020 Competition and Demonstration Track, PMLR, pp. 233\u2013252 (2021). https:\/\/proceedings.mlr.press\/v133\/guss21a"},{"key":"25_CR5","unstructured":"Harter, A., Melnik, A., Kumar, G., Agarwal, D., Garg, A., Ritter, H.: Solving physics puzzles by reasoning about paths. In: 1st NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning (2020). https:\/\/arxiv.org\/abs\/2011.07357"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Hilton, J., Cammarata, N., Carter, S., Goh, G., Olah, C.: Understanding RL vision. Distill (2020). https:\/\/doi.org\/10.23915\/distill.00029, https:\/\/distill.pub\/2020\/understanding-rl-vision","DOI":"10.23915\/distill.00029"},{"key":"25_CR7","unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks. arXiv preprint arXiv:1611.05397 (2016)"},{"key":"25_CR8","unstructured":"Kaiser, L., et al.: Model-based reinforcement learning for Atari. arXiv preprint arXiv:1903.00374 (2019)"},{"key":"25_CR9","unstructured":"Konen, K., Korthals, T., Melnik, A., Schilling, M.: Biologically-inspired deep reinforcement learning of modular control for a six-legged robot. In: 2019 IEEE International Conference on Robotics and Automation Workshop on Learning Legged Locomotion Workshop, (ICRA) 2019, Montreal, CA, 20\u201325 May 2019 (2019)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"K\u00f6nig, P., Melnik, A., Goeke, C., Gert, A.L., K\u00f6nig, S.U., Kietzmann, T.C.: Embodied cognition. In: 2018 6th International Conference on Brain-Computer Interface (BCI), pp. 1\u20134. IEEE (2018)","DOI":"10.1109\/IWW-BCI.2018.8311486"},{"key":"25_CR11","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. CoRR abs\/1210.5644 (2012). http:\/\/arxiv.org\/abs\/1210.5644"},{"key":"25_CR12","unstructured":"Li, S.: Simple introduction about hourglass-like model. https:\/\/medium.com\/@sunnerli\/simple-introduction-about-hourglass-like-model-11ee7c30138"},{"key":"25_CR13","unstructured":"Melnik, A., Bramlage, L., Voss, H., Rossetto, F., Ritter, H.: Combining causal modelling and deep reinforcement learning for autonomous agents in minecraft. In: 4th Workshop on Semantic Policy and Action Representations for Autonomous Robots at IROS 2019 (2019)"},{"key":"25_CR14","unstructured":"Melnik, A., Fleer, S., Schilling, M., Ritter, H.: Modularization of end-to-end learning: case study in arcade games. In: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Workshop on Causal Learning (2018). https:\/\/arxiv.org\/pdf\/1901.09895.pdf"},{"key":"25_CR15","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3389\/frobt.2021.538773","volume":"8","author":"A Melnik","year":"2021","unstructured":"Melnik, A., Lach, L., Plappert, M., Korthals, T., Haschke, R., Ritter, H.: Using tactile sensing to improve the sample efficiency and performance of deep deterministic policy gradients for simulated in-hand manipulation tasks. Front. Robot. AI 8, 57 (2021). https:\/\/doi.org\/10.3389\/frobt.2021.538773","journal-title":"Front. Robot. AI"},{"key":"25_CR16","doi-asserted-by":"publisher","first-page":"253","DOI":"10.3389\/fnbeh.2018.00253","volume":"12","author":"A Melnik","year":"2018","unstructured":"Melnik, A., Sch\u00fcler, F., Rothkopf, C.A., K\u00f6nig, P.: The world as an external memory: the price of saccades in a sensorimotor task. Front. Behav. Neurosci. 12, 253 (2018). https:\/\/doi.org\/10.3389\/fnbeh.2018.00253","journal-title":"Front. Behav. Neurosci."},{"issue":"11","key":"25_CR17","doi-asserted-by":"publisher","first-page":"e7","DOI":"10.23915\/distill.00007","volume":"2","author":"C Olah","year":"2017","unstructured":"Olah, C., Mordvintsev, A., Schubert, L.: Feature visualization. Distill 2(11), e7 (2017)","journal-title":"Distill"},{"issue":"3","key":"25_CR18","doi-asserted-by":"publisher","first-page":"e10","DOI":"10.23915\/distill.00010","volume":"3","author":"C Olah","year":"2018","unstructured":"Olah, C., et al.: The building blocks of interpretability. Distill 3(3), e10 (2018)","journal-title":"Distill"},{"key":"25_CR19","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-319-99316-4_36","volume-title":"Biologically Inspired Cognitive Architectures 2018","author":"M Schilling","year":"2019","unstructured":"Schilling, M., Melnik, A.: An approach to hierarchical deep reinforcement learning for a decentralized walking control architecture. In: Samsonovich, A.V. (ed.) BICA 2018. AISC, vol. 848, pp. 272\u2013282. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-319-99316-4_36"},{"key":"25_CR20","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)"},{"key":"25_CR21","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps (2014)"},{"key":"25_CR22","unstructured":"Srinivas, A., Laskin, M., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. arXiv preprint arXiv:2004.04136 (2020)"},{"key":"25_CR23","unstructured":"taigw: Simple CRF python package. https:\/\/github.com\/HiLab-git\/SimpleCRF"}],"container-title":["Lecture Notes in Computer Science","KI 2021: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87626-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T07:08:12Z","timestamp":1639724892000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87626-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030876258","9783030876265"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87626-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2021.uni-luebeck.de\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","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":"16","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":"4","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":"27% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}