{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:22:05Z","timestamp":1773267725191,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,1,5]],"date-time":"2020-01-05T00:00:00Z","timestamp":1578182400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,1,5]]},"DOI":"10.1145\/3371158.3371168","type":"proceedings-article","created":{"date-parts":[[2020,1,16]],"date-time":"2020-01-16T00:24:22Z","timestamp":1579134262000},"page":"82-89","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning for Single-Shot Diagnosis and Adaptation in Damaged Robots"],"prefix":"10.1145","author":[{"given":"Shresth","family":"Verma","sequence":"first","affiliation":[{"name":"ABV-Indian Institute of Information Technology and Management, Gwalior"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haritha S.","family":"Nair","sequence":"additional","affiliation":[{"name":"ABV-Indian Institute of Information Technology and Management, Gwalior"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaurav","family":"Agarwal","sequence":"additional","affiliation":[{"name":"ABV-Indian Institute of Information Technology and Management, Gwalior"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joydip","family":"Dhar","sequence":"additional","affiliation":[{"name":"ABV-Indian Institute of Information Technology and Management, Gwalior"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anupam","family":"Shukla","sequence":"additional","affiliation":[{"name":"ABV-Indian Institute of Information Technology and Management, Gwalior"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,1,15]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Curriculum Learning. In Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)","author":"Bengio Yoshua","year":"2009"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1308802"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Neural Information Processing Systems 26. Curran Associates","author":"Borji Ali"},{"key":"e_1_3_2_1_4_1","volume-title":"CoRR abs\/1606.01540","author":"Brockman Greg","year":"2016"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Guillaume Chaslot Sander Bakkes Istv\u00e1n Szita and Pieter Spronck. 2008. Monte-Carlo Tree Search: A New Framework for Game AI. In AIIDE.  Guillaume Chaslot Sander Bakkes Istv\u00e1n Szita and Pieter Spronck. 2008. Monte-Carlo Tree Search: A New Framework for Game AI. In AIIDE.","DOI":"10.3233\/ICG-2008-31303"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.11.010"},{"key":"e_1_3_2_1_7_1","volume-title":"Robots that can adapt like animals. Nature 521, 7553 (28","author":"Cully Antoine","year":"2015"},{"key":"e_1_3_2_1_8_1","volume-title":"LSTM: A search space odyssey","author":"Greff Klaus","year":"2017"},{"key":"e_1_3_2_1_9_1","volume-title":"TF-Agents: A library for Reinforcement Learning in TensorFlow. https:\/\/github.com\/tensorflow\/agents. https:\/\/github. com\/tensorflow\/agents [Online","author":"Guadarrama Sergio","year":"2019"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913499192"},{"key":"e_1_3_2_1_13_1","volume-title":"Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning. CoRR abs\/1710.06117","author":"Kume Ayaka","year":"2017"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2851148"},{"key":"e_1_3_2_1_15_1","volume-title":"Bayesian Approach to Global Optimization","author":"Mockus Jonas"},{"key":"e_1_3_2_1_16_1","volume-title":"Illuminating search spaces by mapping elites. CoRR abs\/1504.04909","author":"Mouret Jean-Baptiste","year":"2015"},{"key":"e_1_3_2_1_17_1","volume-title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization. CoRR abs\/1710.06537","author":"Peng Xue Bin","year":"2017"},{"key":"e_1_3_2_1_18_1","volume-title":"Robust Adversarial Reinforcement Learning. ICML","author":"Pinto Lerrel","year":"2017"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research)","volume":"70","author":"Pinto Lerrel"},{"key":"e_1_3_2_1_20_1","volume-title":"Williams","author":"Rasmussen Carl Edward","year":"2005"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research), Francis Bach and David Blei (Eds.)","volume":"37","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_1_22_1","volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","author":"Schulman John","year":"2015"},{"key":"e_1_3_2_1_23_1","volume-title":"Proximal Policy Optimization Algorithms. (07","author":"Schulman John","year":"2017"},{"key":"e_1_3_2_1_24_1","volume-title":"J. Schrit-twieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D. Hassabis.","author":"Silver D.","year":"2016"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning -","volume":"32","author":"Silver David","year":"2014"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","volume-title":"The TEXPLORE Algorithm","author":"Hester T.","DOI":"10.1007\/978-3-319-01168-4_4"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"CoDS COMAD 2020: 7th ACM IKDD CoDS and 25th COMAD","location":"Hyderabad India","acronym":"CoDS COMAD 2020","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 7th ACM IKDD CoDS and 25th COMAD"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3371158.3371168","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3371158.3371168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T19:05:44Z","timestamp":1750273544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3371158.3371168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,5]]},"references-count":28,"alternative-id":["10.1145\/3371158.3371168","10.1145\/3371158"],"URL":"https:\/\/doi.org\/10.1145\/3371158.3371168","relation":{},"subject":[],"published":{"date-parts":[[2020,1,5]]},"assertion":[{"value":"2020-01-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}