{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T04:15:29Z","timestamp":1772338529957,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T00:00:00Z","timestamp":1615161600000},"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":[[2021,3,8]]},"DOI":"10.1145\/3434074.3447207","type":"proceedings-article","created":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T01:33:17Z","timestamp":1615167197000},"page":"430-433","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Active Feedback Learning with Rich Feedback"],"prefix":"10.1145","author":[{"given":"Hang","family":"Yu","sequence":"first","affiliation":[{"name":"Tufts University, Medford, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elaine Schaertl","family":"Short","sequence":"additional","affiliation":[{"name":"Tufts University, Medford, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Applying q (?)-learning in deep reinforcement learning to play Atari games,\" in AAMAS Adaptive Learning Agents (ALA) Workshop","author":"Mousavi S. S.","year":"2017","unstructured":"S. S. Mousavi , M. Schukat , E. Howley , and P. Mannion , \" Applying q (?)-learning in deep reinforcement learning to play Atari games,\" in AAMAS Adaptive Learning Agents (ALA) Workshop , 2017 . S. S. Mousavi, M. Schukat, E. Howley, and P. Mannion, \"Applying q (?)-learning in deep reinforcement learning to play Atari games,\" in AAMAS Adaptive Learning Agents (ALA) Workshop, 2017."},{"key":"e_1_3_2_1_2_1","first-page":"3338","volume-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning,\" Advances in neural information processing systems","author":"Guo X.","year":"2014","unstructured":"X. Guo , S. Singh , H. Lee , R. L. Lewis , and X. Wang , \" Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning,\" Advances in neural information processing systems , vol. 27 , pp. 3338 -- 3346 , 2014 . X. Guo, S. Singh, H. Lee, R. L. Lewis, and X. Wang, \"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning,\" Advances in neural information processing systems, vol. 27, pp. 3338--3346, 2014."},{"key":"e_1_3_2_1_3_1","first-page":"4299","volume-title":"Deep reinforcement learning from human preferences,\" in Advances in Neural Information Processing Systems","author":"Christiano P. F.","year":"2017","unstructured":"P. F. Christiano , J. Leike , T. Brown , M. Martic , S. Legg , and D. Amodei , \" Deep reinforcement learning from human preferences,\" in Advances in Neural Information Processing Systems , 2017 , pp. 4299 -- 4307 . P. F. Christiano, J. Leike, T. Brown, M. Martic, S. Legg, and D. Amodei, \"Deep reinforcement learning from human preferences,\" in Advances in Neural Information Processing Systems, 2017, pp. 4299--4307."},{"key":"e_1_3_2_1_4_1","first-page":"8011","volume-title":"Reward learning from human preferences and demonstrations in Atari,\" in Advances in neural information processing systems","author":"Ibarz B.","year":"2018","unstructured":"B. Ibarz , J. Leike , T. Pohlen , G. Irving , S. Legg , and D. Amodei , \" Reward learning from human preferences and demonstrations in Atari,\" in Advances in neural information processing systems , 2018 , pp. 8011 -- 8023 . B. Ibarz, J. Leike, T. Pohlen, G. Irving, S. Legg, and D. Amodei, \"Reward learning from human preferences and demonstrations in Atari,\" in Advances in neural information processing systems, 2018, pp. 8011--8023."},{"key":"e_1_3_2_1_5_1","volume-title":"Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971","author":"Lillicrap T. P.","year":"2015","unstructured":"T. P. Lillicrap , J. J. Hunt , A. Pritzel , N. Heess , T. Erez , Y. Tassa , D. Silver , and D. Wierstra , \" Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971 , 2015 . T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, Y. Tassa, D. Silver, andD. Wierstra, \"Continuous control with deep reinforcement learning,\" arXiv preprint arXiv:1509.02971, 2015."},{"key":"e_1_3_2_1_6_1","first-page":"1889","volume-title":"Trust region policy optimization,\" in International conference on machine learning","author":"Schulman J.","year":"2015","unstructured":"J. Schulman , S. Levine , P. Abbeel , M. Jordan , and P. Moritz , \" Trust region policy optimization,\" in International conference on machine learning , 2015 , pp. 1889 -- 1897 . J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P. Moritz, \"Trust region policy optimization,\" in International conference on machine learning, 2015, pp. 1889--1897."},{"key":"e_1_3_2_1_7_1","first-page":"267","volume-title":"Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition,\" in Competition and cooperation in neural nets","author":"Fukushima K.","year":"1982","unstructured":"K. Fukushima and S. Miyake , \" Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition,\" in Competition and cooperation in neural nets . Springer , 1982 , pp. 267 -- 285 . K. Fukushima and S. Miyake, \"Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition,\" in Competition and cooperation in neural nets. Springer, 1982, pp. 267--285."},{"key":"e_1_3_2_1_8_1","first-page":"994","volume-title":"Object recognition with features inspired by visual cortex,\" in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","author":"Serre T.","year":"2005","unstructured":"T. Serre , L. Wolf , and T. Poggio , \" Object recognition with features inspired by visual cortex,\" in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) , vol. 2 . Ieee , 2005 , pp. 994 -- 1000 . T. Serre, L. Wolf, and T. Poggio, \"Object recognition with features inspired by visual cortex,\" in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), vol. 2. Ieee, 2005, pp. 994--1000."},{"key":"e_1_3_2_1_9_1","volume-title":"Dulac-Arnold et al., \"Deep q-learning from demonstrations,\" arXiv preprint arXiv:1704.03732","author":"Hester T.","year":"2017","unstructured":"T. Hester , M. Vecerik , O. Pietquin , M. Lanctot , T. Schaul , B. Piot , D. Horgan , J. Quan , A. Sendonaris , G. Dulac-Arnold et al., \"Deep q-learning from demonstrations,\" arXiv preprint arXiv:1704.03732 , 2017 . T. Hester, M. Vecerik,O. Pietquin, M. Lanctot, T. Schaul, B. Piot,D. Horgan, J. Quan, A. Sendonaris, G. Dulac-Arnold et al., \"Deep q-learning from demonstrations,\" arXiv preprint arXiv:1704.03732, 2017."},{"key":"e_1_3_2_1_10_1","volume-title":"Ostrovski et al., \"Human-level control through deep reinforcement learning,\" nature","author":"Mnih V.","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. A. Rusu , J. Veness , M. G. Bellemare , A. Graves , M. Riedmiller , A. K. Fidjeland , G. Ostrovski et al., \"Human-level control through deep reinforcement learning,\" nature , vol. 518 , no. 7540, pp. 529--533, 2015. V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski et al., \"Human-level control through deep reinforcement learning,\" nature, vol. 518, no. 7540, pp. 529--533, 2015."},{"key":"e_1_3_2_1_11_1","volume-title":"Policy shaping with human teachers,\" in Twenty-Fourth International Joint Conference on Artificial Intelligence","author":"Cederborg T.","year":"2015","unstructured":"T. Cederborg , I. Grover , C. L. Isbell , and A. L. Thomaz , \" Policy shaping with human teachers,\" in Twenty-Fourth International Joint Conference on Artificial Intelligence , 2015 . [Online]. Available: https:\/\/www.aaai.org\/ocs\/index.php\/IJCAI\/ IJCAI15\/paper\/viewPaper\/11412 T. Cederborg, I. Grover, C. L. Isbell, and A. L. Thomaz, \"Policy shaping with human teachers,\" in Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015. [Online]. Available: https:\/\/www.aaai.org\/ocs\/index.php\/IJCAI\/ IJCAI15\/paper\/viewPaper\/11412"},{"key":"e_1_3_2_1_12_1","first-page":"2625","volume-title":"Policy shaping: Integrating human feedback with reinforcement learning,\" in Advances in neural information processing systems","author":"Grifth S.","year":"2013","unstructured":"S. Grifth , K. Subramanian , J. Scholz , C. L. Isbell , and A. L. Thomaz , \" Policy shaping: Integrating human feedback with reinforcement learning,\" in Advances in neural information processing systems , 2013 , pp. 2625 -- 2633 . S. Grifth, K. Subramanian, J. Scholz, C. L. Isbell, and A. L. Thomaz, \"Policy shaping: Integrating human feedback with reinforcement learning,\" in Advances in neural information processing systems, 2013, pp. 2625--2633."},{"key":"e_1_3_2_1_13_1","first-page":"292","volume-title":"IEEE","author":"Knox W. B.","year":"2008","unstructured":"W. B. Knox and P. Stone , \" Tamer: Training an agent manually via evaluative reinforcement,\" in 2008 7th IEEE International Conference on Development and Learning . IEEE , 2008 , pp. 292 -- 297 . W. B. Knox and P. Stone, \"Tamer: Training an agent manually via evaluative reinforcement,\" in 2008 7th IEEE International Conference on Development and Learning. IEEE, 2008, pp. 292--297."},{"key":"e_1_3_2_1_14_1","first-page":"447","volume-title":"AAMAS '16","author":"Subramanian K.","year":"2016","unstructured":"K. Subramanian , C. L. Isbell , and A. L. Thomaz , \" Exploration from demonstration for interactive reinforcement learning,\" in Proceedings of the 2016 International Conference on Autonomous Agents amp; Multiagent Systems, ser . AAMAS '16 . Richland, SC: International Foundation for Autonomous Agents and Multiagent Systems , 2016 , p. 447 -- 456 . K. Subramanian, C. L. Isbell, and A. L. Thomaz, \"Exploration from demonstration for interactive reinforcement learning,\" in Proceedings of the 2016 International Conference on Autonomous Agents amp; Multiagent Systems, ser. AAMAS '16. Richland, SC: International Foundation for Autonomous Agents and Multiagent Systems, 2016, p. 447--456."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep reinforcement learning with double q-learning,\" arXiv preprint arXiv:1509.06461","author":"Van Hasselt H.","year":"2015","unstructured":"H. Van Hasselt , A. Guez , and D. Silver , \" Deep reinforcement learning with double q-learning,\" arXiv preprint arXiv:1509.06461 , 2015 . H. Van Hasselt, A. Guez, and D. Silver, \"Deep reinforcement learning with double q-learning,\" arXiv preprint arXiv:1509.06461, 2015."}],"event":{"name":"HRI '21: ACM\/IEEE International Conference on Human-Robot Interaction","location":"Boulder CO USA","acronym":"HRI '21","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion of the 2021 ACM\/IEEE International Conference on Human-Robot Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3434074.3447207","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3434074.3447207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:29Z","timestamp":1750193249000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3434074.3447207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,8]]},"references-count":15,"alternative-id":["10.1145\/3434074.3447207","10.1145\/3434074"],"URL":"https:\/\/doi.org\/10.1145\/3434074.3447207","relation":{},"subject":[],"published":{"date-parts":[[2021,3,8]]},"assertion":[{"value":"2021-03-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}