{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:23:31Z","timestamp":1777487011922,"version":"3.51.4"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,9]]},"DOI":"10.1109\/icdl55364.2023.10364407","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:40:19Z","timestamp":1703533219000},"page":"429-436","source":"Crossref","is-referenced-by-count":5,"title":["A Closer Look at Reward Decomposition for High-Level Robotic Explanations"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Lu","sequence":"first","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xufeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sven","family":"Magg","sequence":"additional","affiliation":[{"name":"Hamburger Informatik Technologie-Center e.V. (HITeC)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Gromniak","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengdi","family":"Li","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"University of Hamburg,Knowledge Technology Group,Department of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref3","article-title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","author":"Qing","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3564240"},{"key":"ref5","first-page":"1","article-title":"Whats on your mind, nico? xhri: A framework for explainable human-robot interaction","volume-title":"KI - K\u00fc nstliche Intelligenz","author":"Gaede","year":"2022"},{"key":"ref6","article-title":"Multi-skill mobile manip-ulation for object rearrangement","author":"Gu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Augmenting reinforcement learning with behavior primitives for diverse manipulation tasks","volume":"abs\/2110.03655","author":"Nasiriany","year":"2021","journal-title":"CoRR"},{"key":"ref8","article-title":"Grad-cam: Why did you say that? visual explanations from deep networks via gradient-based localization","volume":"abs\/1610.02391","author":"Selvaraju","year":"2016","journal-title":"CoRR"},{"key":"ref9","author":"Juozapaitis","year":"2019","journal-title":"Explainable reinforcement learning via reward decomposition"},{"key":"ref10","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref11","article-title":"Fully convolutional networks for semantic segmentation","volume":"abs\/1411.4038","author":"Long","year":"2014","journal-title":"CoRR"},{"key":"ref12","article-title":"The option-critic architecture","volume":"abs\/1609.05140","author":"Bacon","year":"2016","journal-title":"CoRR"},{"key":"ref13","article-title":"Hierarchical goals contextualize local reward decomposition explanations","volume-title":"Neural Computing and Applications","author":"Rietz","year":"2022"},{"key":"ref14","volume-title":"Thinking, fast and slow","author":"Kahneman","year":"2011"},{"key":"ref15","article-title":"Variational intrinsic control","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Workshop Track Proceedings.OpenReview.net","author":"Gregor"},{"key":"ref16","article-title":"Integrated task and motion planning","volume":"abs\/2010.01083","author":"Garrett","year":"2020","journal-title":"CoRR"},{"key":"ref17","article-title":"Rethinking sim2real: Lower fidelity simulation leads to higher sim2real transfer in navigation","author":"Truong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","volume-title":"Proceedings of the Twentieth International Conference on International Conference on Machine Learning, ser. ICML03","author":"Russell"},{"key":"ref19","article-title":"Visualizing and understanding atari agents","volume":"abs\/1711.00138","author":"Greydanus","year":"2017","journal-title":"CoRR"},{"key":"ref20","article-title":"Towards better interpretability in deep q-networks","volume":"abs\/1809.05630","author":"Annasamy","year":"2018","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278776"},{"key":"ref22","article-title":"Explain your move: Understanding agent actions using focused feature saliency","volume":"abs\/1912.12191","author":"Gupta","year":"2019","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref24","article-title":"Rd2: Reward decomposition with representation disentanglement","volume-title":"Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS)","author":"Lin"},{"key":"ref25","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume":"abs\/2010.14406","author":"Zeng","year":"2020","journal-title":"CoRR"},{"key":"ref26","article-title":"Benchmarking in manipulation research: The YCB object and model set and benchmarking protocols","volume-title":"CoRR","volume":"abs\/1502.03143","author":"\u00c7alli","year":"2015"},{"key":"ref27","article-title":"Exploratory not explanatory: Counterfactual analysis of saliency maps for deep RL","volume":"abs\/1912.05743","author":"Atrey","year":"2019","journal-title":"CoRR"},{"key":"ref28","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"1877","article-title":"Language Models are Few-shot Learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","author":"Bubeck","year":"2023","journal-title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4"},{"key":"ref31","article-title":"Chain of thought prompting elicits reasoning in large language models","volume":"abs\/2201.11903","author":"Wei","year":"2022","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342363"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"ref34","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989","journal-title":"Kings College, Oxford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref37","article-title":"Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching","volume":"abs\/1710.01330","author":"Zeng","year":"2017","journal-title":"CoRR"},{"key":"ref38","article-title":"Q-attention: Enabling efficient learning for vision-based robotic manipulation","volume":"abs\/2105.14829","author":"James","year":"2021","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","article-title":"ChatGPT","volume-title":"OpenAI","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981578"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08118-z"}],"event":{"name":"2023 IEEE International Conference on Development and Learning (ICDL)","location":"Macau, China","start":{"date-parts":[[2023,11,9]]},"end":{"date-parts":[[2023,11,11]]}},"container-title":["2023 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10364334\/10364349\/10364407.pdf?arnumber=10364407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T01:43:47Z","timestamp":1706751827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icdl55364.2023.10364407","relation":{},"subject":[],"published":{"date-parts":[[2023,11,9]]}}}