{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:00:50Z","timestamp":1750309250541,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T00:00:00Z","timestamp":1720915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,14]]},"DOI":"10.1145\/3638529.3654045","type":"proceedings-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T16:33:04Z","timestamp":1720456384000},"page":"403-411","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Objective Evolutionary Hindsight Experience Replay for Robot Manipulation Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5944-7291","authenticated-orcid":false,"given":"Erdi","family":"Sayar","sequence":"first","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-1830","authenticated-orcid":false,"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Arjovsky Martin","year":"2017","unstructured":"Arjovsky, Martin and Chintala, Soumith and Bottou, L\u00e9on. 2017. Wasserstein generative adversarial networks. In International Conference on Machine Learning. PMLR, Sydney, Australia, 214--223."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_2_1","DOI":"10.1613\/jair.575"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_3_1","DOI":"10.1109\/TEVC.2017.2704781"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_4_1","DOI":"10.1109\/4235.996017"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_5_1","DOI":"10.1007\/978-3-540-31880-4_11"},{"key":"e_1_3_2_2_6_1","first-page":"8622","article-title":"Adversarial intrinsic motivation for reinforcement learning","volume":"34","author":"Durugkar Ishan","year":"2021","unstructured":"Durugkar, Ishan and Tec, Mauricio and Niekum, Scott and Stone, Peter. 2021. Adversarial intrinsic motivation for reinforcement learning. Advances in Neural Information Processing Systems 34 (2021), 8622--8636.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_7_1","first-page":"2171","article-title":"DEAP: Evolutionary Algorithms Made Easy","volume":"13","author":"F\u00e9lix-Antoine Fortin Michel De","year":"2012","unstructured":"F\u00e9lix-Antoine Fortin, Fran\u00e7ois-Michel De Rainville, Marc-Andr\u00e9 Gardner Gardner, Marc Parizeau, and Christian Gagn\u00e9. 2012. DEAP: Evolutionary Algorithms Made Easy. Journal of Machine Learning Research 13, 1 (2012), 2171--2175.","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_8_1","DOI":"10.1038\/scientificamerican0792-66"},{"key":"e_1_3_2_2_9_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Houthooft Rein","year":"2018","unstructured":"Houthooft, Rein and Chen, Yuhua and Isola, Phillip and Stadie, Bradly and Wolski, Filip and Jonathan Ho, OpenAI and Abbeel, Pieter. 2018. Evolved policy gradients. In Advances in Neural Information Processing Systems, Vol. 31. Neural Information Processing Systems Foundation, San Diego, CA, USA, 10 pages."},{"key":"e_1_3_2_2_10_1","volume-title":"Karen and others","author":"Jaderberg Max","year":"2017","unstructured":"Jaderberg, Max and Dalibard, Valentin and Osindero, Simon and Czarnecki, Wojciech M and Donahue, Jeff and Razavi, Ali and Vinyals, Oriol and Green, Tim and Dunning, Iain and Simonyan, Karen and others. 2017. Population based training of neural networks. arXiv:1711.09846."},{"key":"e_1_3_2_2_11_1","volume-title":"Vijay.","author":"Katoch Sourabh","year":"2021","unstructured":"Katoch, Sourabh and Chauhan, Sumit Singh and Kumar, Vijay. 2021. A review on genetic algorithm: past, present, and future. Multimedia tools and applications 80 (2021), 8091--8126."},{"key":"e_1_3_2_2_12_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Khadka Shauharda","year":"2018","unstructured":"Khadka, Shauharda and Tumer, Kagan. 2018. Evolution-guided policy gradient in reinforcement learning. In Advances in Neural Information Processing Systems, Vol. 31. Neural Information Processing Systems Foundation, San Diego, CA, USA, 13 pages."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1145\/2792984"},{"unstructured":"Lillicrap Timothy P and Hunt Jonathan J and Pritzel Alexander and Heess Nicolas and Erez Tom and Tassa Yuval and Silver David and Wierstra Daan. 2015. Continuous control with deep reinforcement learning. arXiv:1509.02971.","key":"e_1_3_2_2_14_1"},{"key":"e_1_3_2_2_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Wojciech Zaremba","year":"2017","unstructured":"Marcin Andrychowicz and Filip Wolski and Alex Ray and Jonas Schneider and Rachel Fong and Peter Welinder and Bob McGrew and Josh Tobin and Pieter Abbeel and Wojciech Zaremba. 2017. Hindsight Experience Replay. In Advances in Neural Information Processing Systems, Vol. 30. Neural Information Processing Systems Foundation, San Diego, CA, USA, 11 pages."},{"unstructured":"Matthias Plappert and Marcin Andrychowicz and Alex Ray and Bob McGrew and Bowen Baker and Glenn Powell and Jonas Schneider and Josh Tobin and Maciek Chociej and Peter Welinder and Vikash Kumar and Wojciech Zaremba. 2018. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research. arXiv:1802.09464.","key":"e_1_3_2_2_16_1"},{"key":"e_1_3_2_2_17_1","volume-title":"Redmond","author":"Robert McCarthy Qiang Wang","year":"2023","unstructured":"Robert McCarthy, Qiang Wang, and Stephen J. Redmond. 2023. Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks. arXiv:2110.02414."},{"unstructured":"Mnih Volodymyr and Kavukcuoglu Koray and Silver David and Graves Alex and Antonoglou Ioannis and Wierstra Daan and Riedmiller Martin. 2013. Playing Atari with deep reinforcement learning. arXiv:1312.5602.","key":"e_1_3_2_2_18_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_19_1","DOI":"10.1038\/nature14236"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_20_1","DOI":"10.1007\/11552246_35"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1145\/3512290.3528845"},{"key":"e_1_3_2_2_22_1","volume-title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning. In International Conference on Machine Learning, Hal Daum\u00e9 III and Aarti Singh (Eds.)","volume":"119","author":"Silviu Pitis Harris Chan","year":"2020","unstructured":"Silviu Pitis, Harris Chan, Stephen Zhao, Bradly Stadie, and Jimmy Ba. 2020. Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning. In International Conference on Machine Learning, Hal Daum\u00e9 III and Aarti Singh (Eds.), Vol. 119. PMLR, Online, 7750--7761."},{"key":"e_1_3_2_2_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Rajeswaran Aravind","year":"2017","unstructured":"Rajeswaran, Aravind and Lowrey, Kendall and Todorov, Emanuel V and Kakade, Sham M. 2017. Towards generalization and simplicity in continuous control. In Advances in Neural Information Processing Systems, Vol. 30. Neural Information Processing Systems Foundation, San Diego, CA, USA, 12 pages."},{"key":"e_1_3_2_2_24_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Ren Zhizhou","year":"2019","unstructured":"Ren, Zhizhou and Dong, Kefan and Zhou, Yuan and Liu, Qiang and Peng, Jian. 2019. Exploration via Hindsight Goal Generation. In Advances in Neural Information Processing Systems, Vol. 32. Neural Information Processing Systems Foundation, San Diego, CA, USA, 12."},{"unstructured":"Salimans Tim and Ho Jonathan and Chen Xi and Sidor Szymon and Sutskever Ilya. 2017. Evolution strategies as a scalable alternative to reinforcement learning. arXiv:1703.03864.","key":"e_1_3_2_2_25_1"},{"key":"e_1_3_2_2_26_1","volume-title":"Ozgur S and Knoll, Alois.","author":"Sayar Erdi","year":"2023","unstructured":"Sayar, Erdi and Bing, Zhenshan and D'Eramo, Carlo and Oguz, Ozgur S and Knoll, Alois. 2023. Contact Energy Based Hindsight Experience Prioritization. arXiv:2312.02677."},{"key":"e_1_3_2_2_27_1","volume-title":"Universal Value Function Approximators. In International Conference on Machine Learning","volume":"37","author":"Schaul Tom","year":"2015","unstructured":"Schaul, Tom and Horgan, Daniel and Gregor, Karol and Silver, David. 2015. Universal Value Function Approximators. In International Conference on Machine Learning, Vol. 37. PMLR, Lille, France, 1312--1320."},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_28_1","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_2_29_1","volume-title":"Thore and others","author":"Silver David","year":"2018","unstructured":"Silver, David and Hubert, Thomas and Schrittwieser, Julian and Antonoglou, Ioannis and Lai, Matthew and Guez, Arthur and Lanctot, Marc and Sifre, Laurent and Kumaran, Dharshan and Graepel, Thore and others. 2018. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 6419 (2018), 1140--1144."},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Sutton, Richard S and Barto, Andrew G. 2018. Reinforcement learning: An introduction. MIT Press, Cambridge, MA, USA.","key":"e_1_3_2_2_30_1"},{"volume-title":"Hunt and Alexander Pritzel and Nicolas Heess and Tom Erez and Yuval Tassa and David Silver and Daan Wierstra","year":"2019","unstructured":"Timothy P. Lillicrap and Jonathan J. Hunt and Alexander Pritzel and Nicolas Heess and Tom Erez and Yuval Tassa and David Silver and Daan Wierstra. 2019. Continuous control with deep reinforcement learning. arXiv:1509.02971.","key":"e_1_3_2_2_31_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_32_1","DOI":"10.1109\/IROS.2012.6386109"},{"unstructured":"Vecerik Mel and Hester Todd and Scholz Jonathan and Wang Fumin and Pietquin Olivier and Piot Bilal and Heess Nicolas and Roth\u00f6rl Thomas and Lampe Thomas and Riedmiller Martin. 2017. Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv:1707.08817.","key":"e_1_3_2_2_33_1"},{"key":"e_1_3_2_2_34_1","volume-title":"C\u00e9dric and others","author":"Villani","year":"2009","unstructured":"Villani, C\u00e9dric and others. 2009. Optimal transport: old and new. Vol. 338. Springer, Berlin Heidelberg, Germany."},{"key":"e_1_3_2_2_35_1","volume-title":"Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control. In International Conference on Machine Learning","volume":"119","author":"Xu Jie","year":"2020","unstructured":"Xu, Jie and Tian, Yunsheng and Ma, Pingchuan and Rus, Daniela and Sueda, Shinjiro and Matusik, Wojciech. 2020. Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control. In International Conference on Machine Learning, Vol. 119. PMLR, Online, 10607--10616."}],"event":{"sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"acronym":"GECCO '24","name":"GECCO '24: Genetic and Evolutionary Computation Conference","location":"Melbourne VIC Australia"},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638529.3654045","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638529.3654045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:50Z","timestamp":1750291010000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638529.3654045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,14]]},"references-count":35,"alternative-id":["10.1145\/3638529.3654045","10.1145\/3638529"],"URL":"https:\/\/doi.org\/10.1145\/3638529.3654045","relation":{},"subject":[],"published":{"date-parts":[[2024,7,14]]},"assertion":[{"value":"2024-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}