{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T01:09:31Z","timestamp":1761181771886,"version":"build-2065373602"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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":[[2025,9,16]]},"DOI":"10.1109\/icdl63968.2025.11204455","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:07:41Z","timestamp":1761066461000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Intrinsic Reward Decomposition for Soft Robotic Manipulation Tasks"],"prefix":"10.1109","author":[{"given":"Vladimir","family":"Sivtsov","sequence":"first","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]},{"given":"Daniil","family":"Shkolnik","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]},{"given":"Athanasios","family":"Papanikolaou","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]},{"given":"Ivan","family":"Markovic","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]},{"given":"Ivan","family":"Petrovic","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]},{"given":"Enrica","family":"Zereik","sequence":"additional","affiliation":[{"name":"Institute of Marine Engineering (CNR-INM),Italian National Research Council,Genoa,Italy,16149"}]},{"given":"Fabio","family":"Bonsignorio","sequence":"additional","affiliation":[{"name":"University of Zagreb, Faculty of Electrical Engineering and Computing, Unska ulica 3,Zagreb,Croatia,10000"}]}],"member":"263","reference":[{"issue":"30","key":"ref1","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"Journal of machine learning research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341432"},{"key":"ref3","article-title":"Effective multimodal reinforcement learning with modality alignment and importance enhancement","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2302.09318"},{"key":"ref4","first-page":"26","article-title":"Physics-informed model-based reinforcement learning","volume-title":"Learning for Dynamics and Control Conference","author":"Ramesh"},{"key":"ref5","first-page":"52759","article-title":"Behavior alignment via reward function optimization","volume":"36","author":"Gupta","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Intrinsically motivated reinforcement learning","volume":"17","author":"Chentanez","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00063"},{"key":"ref8","article-title":"On learning intrinsic rewards for policy gradient methods","volume":"31","author":"Zheng","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13554"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/robotics8010004"},{"key":"ref11","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","volume":"abs\/1707.08817","author":"Vecer\u00edk","year":"2017","journal-title":"ArXiv"},{"key":"ref12","article-title":"Maximum entropy rl (provably) solves some robust rl problems","author":"Eysenbach","year":"2021","journal-title":"arXiv preprint arXiv:2103.06257"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111663"},{"key":"ref14","first-page":"37631","article-title":"Exploration via elliptical episodic bonuses","volume":"35","author":"Henaff","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Exploration by random network distillation","author":"Burda","year":"2018","journal-title":"arXiv preprint arXiv:1810.12894"},{"key":"ref16","article-title":"Never give up: Learning directed exploration strategies","author":"Badia","year":"2020","journal-title":"arXiv preprint arXiv:2002.06038"},{"key":"ref17","first-page":"16341644","article-title":"Smooth exploration for robotic reinforcement learning","volume-title":"Conference on robot learning","author":"Raffin"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/s23083985"},{"key":"ref19","first-page":"656","article-title":"Q-decomposition for reinforcement learning agents","volume-title":"Proceedings of the 20th international conference on machine learning (ICML-03)","author":"Russell"},{"key":"ref20","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"International conference on machine learning","author":"Pathak"},{"key":"ref21","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"Van Seijen","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Explainable reinforcement learning via reward decomposition","volume-title":"IJCAI\/ECAI Workshop on explainable artificial intelligence","author":"Juozapaitis","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127622"},{"key":"ref24","article-title":"Knowing what not to do: Leverage language model insights for action space pruning in multi-agent reinforcement learning","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2405.16854"},{"key":"ref25","first-page":"2201","article-title":"Evolution gym: A large-scale benchmark for evolving soft robots","volume":"34","author":"Bhatia","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"issue":"268","key":"ref28","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","article-title":"Rlexplore: Accelerating research in intrinsically-motivated reinforcement learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv:2405.19548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0169179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft48309.2020.9116004"}],"event":{"name":"2025 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2025,9,16]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2025,9,19]]}},"container-title":["2025 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204361\/11204347\/11204455.pdf?arnumber=11204455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:23:38Z","timestamp":1761153818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icdl63968.2025.11204455","relation":{},"subject":[],"published":{"date-parts":[[2025,9,16]]}}}