{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T04:47:51Z","timestamp":1766551671067,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031474538"},{"type":"electronic","value":"9783031474545"}],"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\/978-3-031-47454-5_24","type":"book-chapter","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T03:02:20Z","timestamp":1698807740000},"page":"316-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Achieving Goals Using Reward Shaping and\u00a0Curriculum Learning"],"prefix":"10.1007","author":[{"given":"Mihai","family":"Anca","sequence":"first","affiliation":[]},{"given":"Jonathan D.","family":"Thomas","sequence":"additional","affiliation":[]},{"given":"Dabal","family":"Pedamonti","sequence":"additional","affiliation":[]},{"given":"Mark","family":"Hansen","sequence":"additional","affiliation":[]},{"given":"Matthew","family":"Studley","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,2]]},"reference":[{"key":"24_CR1","unstructured":"Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Man\u00e9, D.: Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)"},{"key":"24_CR2","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"7836","key":"24_CR3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41586-020-2939-8","volume":"588","author":"MG Bellemare","year":"2020","unstructured":"Bellemare, M.G., et al.: Autonomous navigation of stratospheric balloons using reinforcement learning. Nature 588(7836), 77\u201382 (2020)","journal-title":"Nature"},{"key":"24_CR4","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"24_CR5","unstructured":"Florensa, C., Held, D., Wulfmeier, M., Zhang, M., Abbeel, P.: Reverse curriculum generation for reinforcement learning. In: Levine, S., Vanhoucke, V., Goldberg, K. (eds.) Proceedings of the 1st Annual Conference on Robot Learning, Proceedings of Machine Learning Research, vol. 78, pp. 482\u2013495. PMLR (2017)"},{"key":"24_CR6","unstructured":"Forestier, S., Portelas, R., Mollard, Y., Oudeyer, P.-Y.: Intrinsically motivated goal exploration processes with automatic curriculum learning. J. Mach. Learn. Res. (2022)"},{"key":"24_CR7","unstructured":"Graves, A., Bellemare, M.G., Menick, J., Munos, R., Kavukcuoglu, K.: Automated curriculum learning for neural networks. In: International Conference on Machine Learning, pp. 1311\u20131320. PMLR (2017)"},{"key":"24_CR8","unstructured":"Grzes, M.: Reward shaping in episodic reinforcement learning (2017)"},{"key":"24_CR9","first-page":"15931","volume":"33","author":"H Yujing","year":"2020","unstructured":"Yujing, H., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. Adv. Neural. Inf. Process. Syst. 33, 15931\u201315941 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"24_CR10","doi-asserted-by":"publisher","first-page":"6724","DOI":"10.1109\/LRA.2020.3015448","volume":"5","author":"A Hundt","year":"2020","unstructured":"Hundt, A., et al.: \u2018good robot!\u2019: efficient reinforcement learning for multi-step visual tasks with sim to real transfer. IEEE Robot. Autom. Lett. 5(4), 6724\u20136731 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Jeong, R., et al.: Self-supervised sim-to-real adaptation for visual robotic manipulation. In: 2020 IEEE international Conference on Robotics and Automation, pp. 2718\u20132724. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197326"},{"key":"24_CR12","unstructured":"Kaelbling, L.P.: Learning to achieve goals. In: IJCAI, vol. 2, pp. 1094\u20131098. Citeseer (1993)"},{"issue":"13","key":"24_CR13","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Nat. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Nat. Acad. Sci."},{"key":"24_CR14","unstructured":"Lee, A.X. et al.: Beyond pick-and-place: tackling robotic stacking of diverse shapes. In: Proceedings of the 5th Conference on Robot Learning, Proceedings of Machine Learning Research, vol. 164 , pp. 1089\u20131131 (2022)"},{"key":"24_CR15","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.inffus.2019.12.004","volume":"58","author":"T Lesort","year":"2020","unstructured":"Lesort, T., Lomonaco, V., Stoian, A., Maltoni, D., Filliat, D., Diaz-Rodriguez, N.: Continual learning for robotics: definition, framework, learning strategies, opportunities and challenges. Inf. fusion 58, 52\u201368 (2020)","journal-title":"Inf. fusion"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Li, R., Jabri, A., Darrell, T., Agrawal, P.: Towards practical multi-object manipulation using relational reinforcement learning. In: 2020 IEEE International Conference on Robotics and Automation, pp. 4051\u20134058. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9197468"},{"key":"24_CR17","unstructured":"Makoviichuk, D., Makoviychuk, V.: Rl-games: a highperformance framework for reinforcement learning (2022)"},{"key":"24_CR18","unstructured":"Makoviychuk, V., et al.: Isaac gym: high performance GPU-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE international Conference on Robotics and Automation, pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"24_CR20","unstructured":"Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M.E., Stone, P.: Curriculum learning for reinforcement learning domains: a framework and survey. arXiv preprint arXiv:2003.04960 (2020)"},{"key":"24_CR21","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"},{"key":"24_CR22","unstructured":"Raffin, A., Hill, A., Traore, R., Lesort, T., Diaz-Rodriguez, N., Filliat, D.: Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics. arXiv preprint arXiv:1901.08651 (2019)"},{"issue":"3","key":"24_CR23","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/70.294207","volume":"10","author":"TD Sanger","year":"1994","unstructured":"Sanger, T.D.: Neural network learning control of robot manipulators using gradually increasing task difficulty. IEEE Trans. Robot. Autom. 10(3), 323\u2013333 (1994)","journal-title":"IEEE Trans. Robot. Autom."},{"key":"24_CR24","doi-asserted-by":"publisher","first-page":"313","DOI":"10.3389\/fpsyg.2013.00313","volume":"4","author":"J Schmidhuber","year":"2013","unstructured":"Schmidhuber, J.: Powerplay: training an increasingly general problem solver by continually searching for the simplest still unsolvable problem. Front. Psychol. 4, 313 (2013)","journal-title":"Front. Psychol."},{"key":"24_CR25","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"24_CR26","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"24_CR27","unstructured":"Stooke, A., Abbeel, P.: Accelerated methods for deep reinforcement learning. arXiv preprint arXiv:1803.02811 (2018)"},{"key":"24_CR28","unstructured":"Tang, Y., Ha, D.: The sensory neuron as a transformer: permutation-invariant neural networks for reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"24_CR29","first-page":"4555","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang, X., Chen, Y., Zhu, W.: A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4555\u20134576 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Networks and Systems","Proceedings of the Future Technologies Conference (FTC) 2023, Volume 1"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47454-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T03:06:08Z","timestamp":1698807968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47454-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031474538","9783031474545"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47454-5_24","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FTC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of the Future Technologies Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"19 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ftc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/FTC","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}