{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:47:34Z","timestamp":1768394854478,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819669479","type":"print"},{"value":"9789819669486","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-6948-6_9","type":"book-chapter","created":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T13:44:32Z","timestamp":1750513472000},"page":"119-133","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Causal Policy Learning from\u00a0Self-play for\u00a0Effective Non-prehensile Planar Manipulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5197-6148","authenticated-orcid":false,"given":"Zepeng","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2373-2779","authenticated-orcid":false,"given":"Yong","family":"Guan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6135-3980","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-8602","authenticated-orcid":false,"given":"Zhiping","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9166-9468","authenticated-orcid":false,"given":"Zhenzhou","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Serhan, B., Pandya, H., Kucukyilmaz, A., Neumann, G.: \u201cPush-to-see: Learning non-prehensile manipulation to enhance instance segmentation via deep q-learning,\u201d in. International Conference on Robotics and Automation (ICRA) 2022, 1513\u20131519 (2022)","DOI":"10.1109\/ICRA46639.2022.9811645"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"J.\u00a0St\u00fcber, C.\u00a0Zito, and R.\u00a0Stolkin, \u201cLet\u2019s push things forward: A survey on robot pushing,\u201d Frontiers in Robotics and AI, vol.\u00a07, 2020","DOI":"10.3389\/frobt.2020.00008"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"P.\u00a0Lertkultanon and Q.-C. Pham, \u201cDynamic non-prehensile object transportation,\u201d in 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV). IEEE, 2014, pp. 1392\u20131397","DOI":"10.1109\/ICARCV.2014.7064519"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"W.\u00a0Yuan, J.\u00a0A. Stork, D.\u00a0Kragic, M.\u00a0Y. Wang, and K.\u00a0Hang, \u201cRearrangement with nonprehensile manipulation using deep reinforcement learning,\u201d in 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2018, pp. 270\u2013277","DOI":"10.1109\/ICRA.2018.8462863"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"W.\u00a0Bejjani, M.\u00a0R. Dogar, and M.\u00a0Leonetti, \u201cLearning physics-based manipulation in clutter: Combining image-based generalization and look-ahead planning,\u201d in 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2019, pp. 6562\u20136569","DOI":"10.1109\/IROS40897.2019.8967717"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"K.\u00a0Lowrey, S.\u00a0Kolev, J.\u00a0Dao, A.\u00a0Rajeswaran, and E.\u00a0Todorov, \u201cReinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system,\u201d in 2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR). IEEE, 2018, pp. 35\u201342","DOI":"10.1109\/SIMPAR.2018.8376268"},{"key":"9_CR7","unstructured":"J.\u00a0Schulman, S.\u00a0Levine, P.\u00a0Abbeel, M.\u00a0Jordan, and P.\u00a0Moritz, \u201cTrust region policy optimization,\u201d in International conference on machine learning. PMLR, 2015, pp. 1889\u20131897"},{"key":"9_CR8","unstructured":"R.\u00a0S. Sutton and A.\u00a0G. Barto, \u201cReinforcement learning: an introduction mit press,\u201d Cambridge, MA, vol. 22447, 1998"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S., \u201cNeural network dynamics for model-based deep reinforcement learning with model-free fine-tuning,\u201d in,: IEEE international conference on robotics and automation (ICRA). IEEE 2018, 7559\u20137566 (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"9_CR10","unstructured":"J.\u00a0K. Li, W.\u00a0S. Lee, and D.\u00a0Hsu, \u201cPush-net: Deep planar pushing for objects with unknown physical properties.\u201d in Robotics: Science and Systems, vol.\u00a014, 2018, pp. 1\u20139"},{"key":"9_CR11","unstructured":"P.\u00a0Florence, C.\u00a0Lynch, A.\u00a0Zeng, O.\u00a0A. Ramirez, A.\u00a0Wahid, L.\u00a0Downs, A.\u00a0Wong, J.\u00a0Lee, I.\u00a0Mordatch, and J.\u00a0Tompson, \u201cImplicit behavioral cloning,\u201d in Conference on Robot Learning. PMLR, 2022, pp. 158\u2013168"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"C.\u00a0Chi, Z.\u00a0Xu, S.\u00a0Feng, E.\u00a0Cousineau, Y.\u00a0Du, B.\u00a0Burchfiel, R.\u00a0Tedrake, and S.\u00a0Song, \u201cDiffusion policy: Visuomotor policy learning via action diffusion,\u201d The International Journal of Robotics Research, 2024","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"9_CR13","first-page":"9180","volume":"33","author":"Y Li","year":"2020","unstructured":"Li, Y., Torralba, A., Anandkumar, A., Fox, D., Garg, A.: Causal discovery in physical systems from videos. Adv. Neural. Inf. Process. Syst. 33, 9180\u20139192 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"M.\u00a0Toromanoff, E.\u00a0Wirbel, and F.\u00a0Moutarde, \u201cEnd-to-end model-free reinforcement learning for urban driving using implicit affordances,\u201d in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 7153\u20137162","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Chen, J., Yuan, B., Tomizuka, M., \u201cModel-free deep reinforcement learning for urban autonomous driving,\u201d in,: IEEE intelligent transportation systems conference (ITSC). IEEE 2019, 2765\u20132771 (2019)","DOI":"10.1109\/ITSC.2019.8917306"},{"issue":"39","key":"9_CR16","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"9_CR17","unstructured":"M.\u00a0Neunert, A.\u00a0Abdolmaleki, M.\u00a0Wulfmeier, T.\u00a0Lampe, T.\u00a0Springenberg, R.\u00a0Hafner, F.\u00a0Romano, J.\u00a0Buchli, N.\u00a0Heess, and M.\u00a0Riedmiller, \u201cContinuous-discrete reinforcement learning for hybrid control in robotics,\u201d in Conference on Robot Learning. PMLR, 2020, pp. 735\u2013751"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"C.\u00a0Banerjee, Z.\u00a0Chen, and N.\u00a0Noman, \u201cBoosting exploration in actor-critic algorithms by incentivizing plausible novel states,\u201d in 2023 62nd IEEE Conference on Decision and Control (CDC). IEEE, 2023, pp. 7009\u20137014","DOI":"10.1109\/CDC49753.2023.10383350"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"C.\u00a0Banerjee and Chen, \u201cImproved soft actor-critic: Mixing prioritized off-policy samples with on-policy experiences,\u201d IEEE Transactions on Neural Networks and Learning Systems, vol.\u00a035, no.\u00a03, pp. 3121\u20133129, 2022","DOI":"10.1109\/TNNLS.2022.3174051"},{"issue":"6","key":"9_CR20","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1109\/TETCI.2022.3140375","volume":"6","author":"C Banerjee","year":"2022","unstructured":"Banerjee, C., Chen, Z., Noman, N., Zamani, M.: Optimal actor-critic policy with optimized training datasets. IEEE Transactions on Emerging Topics in Computational Intelligence 6(6), 1324\u20131334 (2022)","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"C.\u00a0Banerjee, K.\u00a0Nguyen, C.\u00a0Fookes, and M.\u00a0Raissi, \u201cA survey on physics informed reinforcement learning: Review and open problems,\u201d arXiv preprint arXiv:2309.01909, 2023","DOI":"10.2139\/ssrn.4597487"},{"key":"9_CR22","unstructured":"G.\u00a0Gokhale, B.\u00a0Claessens, and C.\u00a0Develder, \u201cPhysq: a physics informed reinforcement learning framework for building control,\u201d arXiv preprint arXiv:2211.11830, 2022"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"D.\u00a0Cao, J.\u00a0Zhao, J.\u00a0Hu, Y.\u00a0Pei, Q.\u00a0Huang, Z.\u00a0Chen, and W.\u00a0Hu, \u201cPhysics-informed graphical representation-enabled deep reinforcement learning for robust distribution system voltage control,\u201d IEEE Transactions on Smart Grid, 2023","DOI":"10.1109\/PESGM51994.2024.10689112"},{"key":"9_CR24","unstructured":"A.\u00a0Ramesh and B.\u00a0Ravindran, \u201cPhysics-informed model-based reinforcement learning,\u201d in Learning for Dynamics and Control Conference. PMLR, 2023, pp. 26\u201337"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Xie, C., Patil, S., Moldovan, T., Levine, S., Abbeel, P., \u201cModel-based reinforcement learning with parametrized physical models and optimism-driven exploration,\u201d in,: IEEE international conference on robotics and automation (ICRA). IEEE 2016, 504\u2013511 (2016)","DOI":"10.1109\/ICRA.2016.7487172"},{"key":"9_CR26","unstructured":"D.\u00a0A. Pomerleau, \u201cAlvinn: An autonomous land vehicle in a neural network,\u201d Advances in neural information processing systems, vol.\u00a01, 1988"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"T.\u00a0Osa, J.\u00a0Pajarinen, G.\u00a0Neumann, J.\u00a0A. Bagnell, P.\u00a0Abbeel, J.\u00a0Peters et\u00a0al., \u201cAn algorithmic perspective on imitation learning,\u201d Foundations and Trends\u00ae in Robotics, vol.\u00a07, no. 1-2, pp. 1\u2013179, 2018","DOI":"10.1561\/2300000053"},{"issue":"4","key":"9_CR28","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Van de Panne, M.: Deepmimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Transactions On Graphics (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Transactions On Graphics (TOG)"},{"issue":"4","key":"9_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459670","volume":"40","author":"XB Peng","year":"2021","unstructured":"Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: Amp: Adversarial motion priors for stylized physics-based character control. ACM Transactions on Graphics (ToG) 40(4), 1\u201320 (2021)","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"9_CR30","unstructured":"C.\u00a0Atkeson and C.\u00a0Atkeson, \u201cWhat advice would i give a starting graduate student interested in robot learning?\u201d in Robotics Retrospectives-Workshop at RSS 2020"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"A.\u00a0Rajeswaran, V.\u00a0Kumar, A.\u00a0Gupta, G.\u00a0Vezzani, J.\u00a0Schulman, E.\u00a0Todorov, and S.\u00a0Levine, \u201cLearning complex dexterous manipulation with deep reinforcement learning and demonstrations,\u201d arXiv preprint arXiv:1709.10087, 2017","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"9_CR32","unstructured":"J.\u00a0Song, H.\u00a0Ren, D.\u00a0Sadigh, and S.\u00a0Ermon, \u201cMulti-agent generative adversarial imitation learning,\u201d Advances in neural information processing systems, vol.\u00a031, 2018"},{"key":"9_CR33","unstructured":"J.\u00a0Fu, A.\u00a0Kumar, O.\u00a0Nachum, G.\u00a0Tucker, and S.\u00a0Levine, \u201cD4rl: Datasets for deep data-driven reinforcement learning,\u201d arXiv preprint arXiv:2004.07219, 2020"},{"key":"9_CR34","unstructured":"J.\u00a0Sohl-Dickstein, E.\u00a0Weiss, N.\u00a0Maheswaranathan, and S.\u00a0Ganguli, \u201cDeep unsupervised learning using nonequilibrium thermodynamics,\u201d in International conference on machine learning. PMLR, 2015, pp. 2256\u20132265"},{"key":"9_CR35","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR36","unstructured":"M.\u00a0Janner, Y.\u00a0Du, J.\u00a0B. Tenenbaum, and S.\u00a0Levine, \u201cPlanning with diffusion for flexible behavior synthesis,\u201d arXiv preprint arXiv:2205.09991, 2022"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"J.\u00a0Urain, N.\u00a0Funk, J.\u00a0Peters, and G.\u00a0Chalvatzaki, \u201cSe (3)-diffusionfields: Learning smooth cost functions for joint grasp and motion optimization through diffusion,\u201d in 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023, pp. 5923\u20135930","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"S.\u00a0Huang, Z.\u00a0Wang, P.\u00a0Li, B.\u00a0Jia, T.\u00a0Liu, Y.\u00a0Zhu, W.\u00a0Liang, and S.-C. Zhu, \u201cDiffusion-based generation, optimization, and planning in 3d scenes,\u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 16\u00a0750\u201316\u00a0761","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"9_CR39","unstructured":"Z.\u00a0Wang, J.\u00a0J. Hunt, and M.\u00a0Zhou, \u201cDiffusion policies as an expressive policy class for offline reinforcement learning,\u201d arXiv preprint arXiv:2208.06193, 2022"},{"key":"9_CR40","unstructured":"A.\u00a0Mandlekar, D.\u00a0Xu, J.\u00a0Wong, S.\u00a0Nasiriany, C.\u00a0Wang, R.\u00a0Kulkarni, L.\u00a0Fei-Fei, S.\u00a0Savarese, Y.\u00a0Zhu, and R.\u00a0Mart\u00edn-Mart\u00edn, \u201cWhat matters in learning from offline human demonstrations for robot manipulation,\u201d arXiv preprint arXiv:2108.03298, 2021"}],"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\/978-981-96-6948-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T08:07:19Z","timestamp":1768378039000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6948-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819669479","9789819669486"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6948-6_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 June 2025","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":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}