{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:31:18Z","timestamp":1761895878943,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210033","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Causal Reasoning-Guided Intrinsic Goals for Efficient Task Completion in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tong","family":"Wu","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Wen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangchun","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuran","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dayong","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Software Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref2","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"International conference on machine learning","author":"Ostrovski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Diversity is all you need: Learning skills without a reward function","year":"2018","author":"Eysenbach","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3527154"},{"key":"ref6","article-title":"Minimalistic grid-world environment for openai gym (2018)","volume-title":"URL https:\/\/github.com\/maximecb\/gym-minigrid","volume":"6","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref7","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"International conference on machine learning","author":"Cobbe"},{"article-title":"Automatic goal generation for reinforcement learning agents","year":"2018","author":"Florensa","key":"ref8"},{"article-title":"Learning with amigo: Adversarially motivated intrinsic goals","year":"2021","author":"Campero","key":"ref9"},{"key":"ref10","first-page":"33 947","article-title":"Improving intrinsic exploration with language abstractions","volume":"35","author":"Mu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Causal reinforcement learning: A survey","year":"2023","author":"Deng","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25924"},{"article-title":"Q-cogni: An integrated causal reinforcement learning framework","year":"2023","author":"Cunha","key":"ref13"},{"article-title":"Ella: Exploration through learned language abstraction","year":"2021","author":"Mirchandani","key":"ref14"},{"article-title":"Babyai: A platform to study the sample efficiency of grounded language learning","year":"2019","author":"Chevalier-Boisvert","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-040120-010930"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1257\/0002828041464669"},{"article-title":"Torchbeast: A pytorch platform for distributed rl","year":"2019","author":"K\u00fcttler","key":"ref18"},{"article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","year":"2018","author":"Espeholt","key":"ref19"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref20"},{"article-title":"Ride: Rewarding impact-driven exploration for procedurally-generated environments","year":"2020","author":"Raileanu","key":"ref21"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210033.pdf?arnumber=11210033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:00:59Z","timestamp":1761890459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210033","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}