{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:57:35Z","timestamp":1768406255429,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341628","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:17:55Z","timestamp":1702495075000},"page":"9324-9331","source":"Crossref","is-referenced-by-count":7,"title":["Control Transformer: Robot Navigation in Unknown Environments Through PRM-Guided Return-Conditioned Sequence Modeling"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Lawson","sequence":"first","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed H.","family":"Qureshi","sequence":"additional","affiliation":[{"name":"Purdue University,Department of Computer Science,West Lafayette,IN,USA,47907"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref2","article-title":"Skill discovery for exploration and planning using deep skill graphs","volume-title":"ICML","author":"Bagaria","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0110"},{"key":"ref4","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref5","volume-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans","year":"2016-2021"},{"key":"ref6","article-title":"Rvs: What is essential for offline rl via supervised learning?","volume-title":"International Conference on Learning Representations","author":"Emmons","year":"2021"},{"key":"ref7","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations","author":"Eysenbach","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref9","volume-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref10","article-title":"Learning to reach goals via iterated supervised learning","volume-title":"International Conference on Learning Representations","author":"Ghosh","year":"2020"},{"key":"ref11","article-title":"Variational intrinsic control","volume":"abs\/1611.07507","author":"Gregor","year":"2017","journal-title":"ArXiv"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/make4010009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460730"},{"key":"ref16","article-title":"Offline reinforcement learning as one big sequence modeling problem","author":"Janner","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Motion planning transformers: One model to plan them all","volume":"abs\/2106.02791","author":"Johnson","year":"2021","journal-title":"ArXiv"},{"key":"ref18","article-title":"Kaelbling. Learning to achieve goals","volume-title":"IJCAI","author":"Pack","year":"1993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref20","article-title":"Reward-conditioned policies","volume":"abs\/1912.13465","author":"Kumar","year":"2019","journal-title":"ArXiv"},{"key":"ref21","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Rapidly-exploring random trees: a new tool for path planning","author":"LaValle","year":"1998","journal-title":"The annual research report"},{"key":"ref23","article-title":"Multi-game decision transformers","volume-title":"Advances in Neural Information Processing Systems","author":"Lee","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-013-9822-x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref26","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"NeurIPS","author":"Nachum","year":"2018"},{"key":"ref27","article-title":"Planning with goal-conditioned policies","volume":"32","author":"Nasiriany","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"International conference on machine learning","author":"Parisotto","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2019.8793889"},{"key":"ref30","article-title":"Composing task-agnostic policies with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Ahmed"},{"key":"ref31","volume-title":"Improving language under-standing by generative pre-training","author":"Radford","year":"2018"},{"issue":"268","key":"ref32","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":"ref33","article-title":"Can wikipedia help offline reinforcement learning?","volume":"abs\/2201.12122","author":"Reid","year":"2022","journal-title":"ArXiv"},{"key":"ref34","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ross","year":"2010"},{"key":"ref35","article-title":"Reinforcement learning upside down: Dont predict rewards - just map them to actions","volume":"abs\/1912.02875","author":"Schmidhuber","year":"2019","journal-title":"ArXiv"},{"key":"ref36","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"International Conference on Learning Representations","author":"Sharma","year":"2019"},{"key":"ref37","article-title":"Training agents using upside-down reinforcement learning","volume":"abs\/1912.02877","author":"Srivastava","year":"2019","journal-title":"CoRR"},{"key":"ref38","article-title":"Attention is all you need","volume-title":"NIPS","author":"Vaswani","year":"2017"},{"key":"ref39","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets","year":"2017"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341628.pdf?arnumber=10341628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:15:46Z","timestamp":1703031346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341628","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}