{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:53:25Z","timestamp":1730296405680,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T00:00:00Z","timestamp":1704672000000},"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":[[2024,1,8]]},"DOI":"10.1109\/sii58957.2024.10417511","type":"proceedings-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T18:22:18Z","timestamp":1707502938000},"page":"1219-1226","source":"Crossref","is-referenced-by-count":0,"title":["Goal-Oriented Task Planning for Composable Robot Control System Using Module-Based Control-as-Inference Framework"],"prefix":"10.1109","author":[{"given":"Taiki","family":"Yano","sequence":"first","affiliation":[{"name":"Research & Development Group, Hitachi, Ltd.,Kokubunji, Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiyoto","family":"Ito","sequence":"additional","affiliation":[{"name":"Research & Development Group, Hitachi, Ltd.,Kokubunji, Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9816.003.0050"},{"volume-title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","year":"2018","author":"Levine","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"journal-title":"ChatGPT for Robotics: Design Principles and Model Abilities","year":"2023","author":"Vemprala","key":"ref4"},{"key":"ref5","first-page":"1","article-title":"RoboNet: Large-Scale Multi-Robot Learning","author":"Dasari","year":"2019","journal-title":"CoRL"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"issue":"1","key":"ref8","first-page":"181","article-title":"Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in RL","volume":"1","author":"Sutton","year":"1999","journal-title":"Statewide Agricultural Land Use Baseline 2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196681"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2361"},{"volume-title":"Assured autonomy in multiagent systems with safe learning","year":"2022","author":"Fiaz","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SII55687.2023.10039413"},{"key":"ref15","first-page":"229","article-title":"Modular multitask reinforcement learning with policy sketches","volume-title":"34th International Conference on Machine Learning, ICML 2017","volume":"1","author":"Andreas","year":"2017"},{"key":"ref16","first-page":"7419","article-title":"TACO: Learning task decomposition via temporal alignment for control","volume-title":"35th International Conference on Machine Learning, ICML 2018","volume":"10","author":"Shiarlis","year":"2018"},{"key":"ref17","first-page":"5842","article-title":"Composable planning with attributes","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aax8177"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref22","first-page":"8582","article-title":"Learning robot skills with temporal variational inference","volume-title":"37th International Conference on Machine Learning, ICML 2020","volume":"PartF16814","author":"Shankar","year":"2020"},{"volume-title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","year":"2021","author":"Chebotar","key":"ref23"},{"key":"ref24","first-page":"1","author":"Sharma","year":"2019","journal-title":"Dynamics-Aware Unsupervised Discovery of Skills"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146589"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636037"},{"key":"ref27","first-page":"1","author":"Ahn","year":"2022","journal-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2787"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00912"},{"key":"ref31","article-title":"Deep active inference agents using Monte-Carlo methods","author":"Fountas","year":"2020","journal-title":"arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/e22050564"},{"issue":"Ml","key":"ref33","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings","author":"Kingma","year":"2014"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0176"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"ref36","first-page":"1","article-title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","author":"Gupta","year":"2019","journal-title":"CoRL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","first-page":"1","author":"Schulman","year":"2017","journal-title":"Proximal Policy Optimization Algorithms"},{"key":"ref39","first-page":"21 847","article-title":"Accelerating Robotic Re-inforcement Learning via Parameterized Action Primitives","volume":"26","author":"Dalal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2024,1,8]]},"location":"Ha Long, Vietnam","end":{"date-parts":[[2024,1,11]]}},"container-title":["2024 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10417130\/10417144\/10417511.pdf?arnumber=10417511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T10:53:51Z","timestamp":1707821631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10417511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,8]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/sii58957.2024.10417511","relation":{},"subject":[],"published":{"date-parts":[[2024,1,8]]}}}