{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:44:07Z","timestamp":1756993447177,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434204"},{"type":"electronic","value":"9783031434211"}],"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\/978-3-031-43421-1_34","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"573-589","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Eigensubspace of\u00a0Temporal-Difference Dynamics and\u00a0How It Improves Value Approximation in\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Qiang","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Setareh","family":"Maghsudi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"unstructured":"Agarwal, A., Jiang, N., Kakade, S.M., Sun, W.: Reinforcement learning: theory and algorithms. CS Dept., UW Seattle, Seattle, WA, USA, Tech. Rep., pp. 10\u20134 (2019)","key":"34_CR1"},{"unstructured":"Agarwal, A., Kakade, S.M., Krishnamurthy, A., Sun, W.: FLAMBE: structural complexity and representation learning of low rank MDPs. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6\u201312 December 2020, virtual (2020)","key":"34_CR2"},{"unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6\u201311 August 2017, Proceedings of Machine Learning Research, vol. 70, pp. 449\u2013458, PMLR (2017)","key":"34_CR3"},{"unstructured":"Brockman, G., et al.: OpenAI gym (2016)","key":"34_CR4"},{"unstructured":"Chen, X., Wang, C., Zhou, Z., Ross, K.W.: Randomized ensembled double Q-learning: learning fast without a model. In: International Conference on Learning Representations (2020)","key":"34_CR5"},{"doi-asserted-by":"crossref","unstructured":"Dabney, W., Ostrovski, G., Silver, D., Munos, R.: Implicit quantile networks for distributional reinforcement learning. In: International Conference on Machine Learning, pp. 1096\u20131105. PMLR (2018)","key":"34_CR6","DOI":"10.1609\/aaai.v32i1.11791"},{"doi-asserted-by":"crossref","unstructured":"Dabney, W., Rowland, M., Bellemare, M., Munos, R.: Distributional reinforcement learning with quantile regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","key":"34_CR7","DOI":"10.1609\/aaai.v32i1.11791"},{"unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, Proceedings of Machine Learning Research, vol. 80, pp. 1406\u20131415. PMLR (2018)","key":"34_CR8"},{"unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, Proceedings of Machine Learning Research, vol. 80, pp. 1582\u20131591. PMLR (2018)","key":"34_CR9"},{"unstructured":"Ghosh, D., Bellemare, M.G.: Representations for stable off-policy reinforcement learning. In: International Conference on Machine Learning, pp. 3556\u20133565. PMLR (2020)","key":"34_CR10"},{"unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, Proceedings of Machine Learning Research, vol. 80, pp. 1856\u20131865. PMLR (2018)","key":"34_CR11"},{"key":"34_CR12","first-page":"2613","volume":"23","author":"H Hasselt","year":"2010","unstructured":"Hasselt, H.: Double Q-learning. Adv. Neural. Inf. Process. Syst. 23, 2613\u20132621 (2010)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"He, Q., Hou, X.: WD3: taming the estimation bias in deep reinforcement learning. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 391\u2013398. IEEE (2020)","key":"34_CR13","DOI":"10.1109\/ICTAI50040.2020.00068"},{"unstructured":"He, Q., Su, H., Zhang, J., Hou, X.: Representation gap in deep reinforcement learning. CoRR abs\/2205.14557 (2022)","key":"34_CR14"},{"doi-asserted-by":"crossref","unstructured":"He, Q., Su, H., Zhang, J., Hou, X.: Frustratingly easy regularization on representation can boost deep reinforcement learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20215\u201320225 (2023)","key":"34_CR15","DOI":"10.1109\/CVPR52729.2023.01936"},{"issue":"2","key":"34_CR16","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1214\/aoms\/1177731457","volume":"14","author":"PG Hoel","year":"1943","unstructured":"Hoel, P.G.: On indices of dispersion. Ann. Math. Stat. 14(2), 155\u2013162 (1943)","journal-title":"Ann. Math. Stat."},{"unstructured":"Kuznetsov, A., Shvechikov, P., Grishin, A., Vetrov, D.: Controlling overestimation bias with truncated mixture of continuous distributional quantile critics. In: Proceedings of the 37th International Conference on Machine Learning, pp. 5556\u20135566 (2020)","key":"34_CR17"},{"unstructured":"Lan, Q., Pan, Y., Fyshe, A., White, M.: Maxmin Q-learning: Controlling the estimation bias of Q-learning. In: International Conference on Learning Representations (2019)","key":"34_CR18"},{"unstructured":"Lyle, C., Rowland, M., Dabney, W.: Understanding and preventing capacity loss in reinforcement learning. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)","key":"34_CR19"},{"unstructured":"Lyle, C., Rowland, M., Dabney, W., Kwiatkowska, M., Gal, Y.: Learning dynamics and generalization in deep reinforcement learning. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesv\u00e1ri, C., Niu, G., Sabato, S. (eds.) International Conference on Machine Learning, ICML 2022, 17\u201323 July 2022, Baltimore, Maryland, USA, Proceedings of Machine Learning Research, vol. 162, pp. 14560\u201314581. PMLR (2022)","key":"34_CR20"},{"unstructured":"Lyle, C., Rowland, M., Ostrovski, G., Dabney, W.: On the effect of auxiliary tasks on representation dynamics. In: International Conference on Artificial Intelligence and Statistics, pp. 1\u20139. PMLR (2021)","key":"34_CR21"},{"doi-asserted-by":"crossref","unstructured":"Meyer, C.D.: Matrix analysis and applied linear algebra, vol. 71. Siam (2000)","key":"34_CR22","DOI":"10.1137\/1.9780898719512"},{"doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","key":"34_CR23","DOI":"10.1038\/nature14236"},{"unstructured":"Munos, R., Stepleton, T., Harutyunyan, A., Bellemare, M.G.: Safe and efficient off-policy reinforcement learning. In: Lee, D.D., Sugiyama, M., von Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 5\u201310 December 2016, Barcelona, Spain, pp. 1046\u20131054 (2016)","key":"34_CR24"},{"unstructured":"Ren, T., Zhang, T., Lee, L., Gonzalez, J.E., Schuurmans, D., Dai, B.: Spectral decomposition representation for reinforcement learning. In: International Conference on Learning Representations (2023)","key":"34_CR25"},{"unstructured":"Sekhari, A., Dann, C., Mohri, M., Mansour, Y., Sridharan, K.: Agnostic reinforcement learning with low-rank MDPs and rich observations. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, 6\u201314 December 2021, virtual, pp. 19033\u201319045 (2021)","key":"34_CR26"},{"issue":"6419","key":"34_CR27","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"key":"34_CR28","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S Singh","year":"2000","unstructured":"Singh, S., Jaakkola, T., Littman, M.L., Szepesv\u00e1ri, C.: Convergence results for single-step on-policy reinforcement-learning algorithms. Mach. Learn. 38, 287\u2013308 (2000)","journal-title":"Mach. Learn."},{"unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press (2018)","key":"34_CR29"},{"issue":"3","key":"34_CR30","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2012, Vilamoura, Algarve, Portugal, 7\u201312 October 2012, pp. 5026\u20135033. IEEE (2012)","key":"34_CR31","DOI":"10.1109\/IROS.2012.6386109"},{"doi-asserted-by":"crossref","unstructured":"Tunyasuvunakool, S., et al.: dm-control: software and tasks for continuous control. Softw. Impacts 6, 100022 (2020). ISSN 2665\u20139638","key":"34_CR32","DOI":"10.1016\/j.simpa.2020.100022"},{"unstructured":"Uehara, M., Zhang, X., Sun, W.: Representation learning for online and offline RL in low-rank MDPs. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)","key":"34_CR33"},{"doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","key":"34_CR34","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"7782","key":"34_CR35","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"doi-asserted-by":"crossref","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","key":"34_CR36","DOI":"10.1007\/BF00992698"},{"unstructured":"Yang, G., Ajay, A., Agrawal, P.: Overcoming the spectral bias of neural value approximation. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)","key":"34_CR37"},{"unstructured":"Yarats, D., Kostrikov, I.: Soft actor-critic (sac) implementation in PyTorch (2020)","key":"34_CR38"},{"unstructured":"Zhang, W., He, J., Zhou, D., Zhang, A., Gu, Q.: Provably efficient representation learning in low-rank Markov decision processes. arXiv preprint arXiv:2106.11935 (2021)","key":"34_CR39"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43421-1_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:48:46Z","timestamp":1694983726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43421-1_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434204","9783031434211"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43421-1_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This work investigates the eigensubspace of the Temporal-Difference algorithm of reinforcement learning and how it improves DRL. The experimental part only uses a physical simulation engine DMControl. Therefore this work does not involve any personal information. This work may be used in areas such as autonomous vehicles, games, and robot control.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"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":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","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":"196","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":"24% - 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":"3.63","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":"4.5","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":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted 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)"}}]}}