{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:58:23Z","timestamp":1723269503722},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"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":[[2020,12,1]]},"DOI":"10.1109\/ssci47803.2020.9308603","type":"proceedings-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T23:12:38Z","timestamp":1609888358000},"source":"Crossref","is-referenced-by-count":5,"title":["HIGhER: Improving instruction following with Hindsight Generation for Experience Replay"],"prefix":"10.1109","author":[{"given":"Geoffrey","family":"Cideron","sequence":"first","affiliation":[]},{"given":"Mathieu","family":"Seurin","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Strub","sequence":"additional","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7979","article-title":"Understanding natural language commands for robotic navigation and mobile manipulation","author":"tellex","year":"2011","journal-title":"Proc Of AAAI"},{"key":"ref38","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11671","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"Proc Of AAAI"},{"key":"ref32","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc of ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11263"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref37","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc of ICLR"},{"key":"ref36","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"Proc of ICML"},{"key":"ref35","article-title":"Visual hindsight experience replay","author":"sahni","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref34","article-title":"Hindsight policy gradients","author":"rauber","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11832","article-title":"Gated-attention architectures for task-oriented language grounding","author":"chaplot","year":"2018","journal-title":"Proc Of AAAI"},{"key":"ref40","article-title":"Reinforced cross-modal matching and self-supervised imitation learning for visionlanguage navigation","author":"wang","year":"2019","journal-title":"Proc of CVPR"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v25i1.7974","article-title":"Learning to interpret natural language navigation instructions from observations","author":"chen","year":"2011","journal-title":"Proc Of AAAI"},{"key":"ref12","article-title":"BabyAI: First steps towards grounded language learning with a human in the loop","author":"chevalier-boisvert","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref13","article-title":"Guiding policies with language via metalearning","author":"co-reyes","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of NAACL"},{"key":"ref15","article-title":"Dher: Hindsight experience replay for dynamic goals","author":"fang","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref16","article-title":"Speaker-follower models for vision-andlanguage navigation","author":"fried","year":"2018","journal-title":"Proc of NeurIPS"},{"key":"ref17","article-title":"From language to goals: Inverse reinforcement learning for vision-based instruction following","author":"fu","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref18","article-title":"Deep reinforcement learning with double q-learning","author":"hasselt","year":"2016","journal-title":"Proc Of AAAI"},{"key":"ref19","article-title":"Grounded language learning in a simulated 3d world","author":"hermann","year":"2017","journal-title":"arXiv preprint arXiv 1706 06551"},{"key":"ref28","article-title":"Competitive experience replay","author":"liu","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2015.03.016"},{"key":"ref3","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref6","article-title":"Systematic generalization: What is required and can it be learned","author":"bahdanau","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref5","article-title":"Learning to understand goal specifications by modelling reward","author":"bahdanau","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref8","article-title":"Home: a household multimodal environment","author":"brodeur","year":"2017","journal-title":"ViGIL Workshop"},{"key":"ref7","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc of NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref9","article-title":"Actrce: Augmenting experience via teacher’s advice for multi-goal reinforcement learning","author":"chan","year":"2018","journal-title":"Goal Specifications for RL workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref20","article-title":"Learning to follow directions in street view","author":"hermann","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref22","article-title":"Understanding grounded language learning agents","author":"hill","year":"2017","journal-title":"arXiv preprint arXiv 1710 09867"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11757","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Proc Of AAAI"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1286"},{"key":"ref24","article-title":"Compositional attention networks for machine reasoning","author":"hudson","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref41","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc of ICML"},{"key":"ref23","author":"hill","year":"2020","journal-title":"Human instruction-following with deep reinforcement learning via transfer-learning from text"},{"key":"ref26","article-title":"Virtual embodiment: A scalable long-term strategy for artificial intelligence research","author":"kiela","year":"2016","journal-title":"arXiv preprint arXiv 1610 07214"},{"key":"ref25","article-title":"Language as an abstraction for hierarchical deep reinforcement learning","author":"jiang","year":"2019","journal-title":"Proc of NeurIPS"}],"event":{"name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Canberra, ACT, Australia","start":{"date-parts":[[2020,12,1]]},"end":{"date-parts":[[2020,12,4]]}},"container-title":["2020 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9308061\/9308107\/09308603.pdf?arnumber=9308603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,10]],"date-time":"2022-12-10T17:31:57Z","timestamp":1670693517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9308603\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ssci47803.2020.9308603","relation":{},"subject":[],"published":{"date-parts":[[2020,12,1]]}}}