{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:37:14Z","timestamp":1730299034933,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"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":[[2023,12,5]]},"DOI":"10.1109\/ssci52147.2023.10371913","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T14:30:22Z","timestamp":1704119422000},"page":"1435-1442","source":"Crossref","is-referenced-by-count":0,"title":["MEWA: A Benchmark For Meta-Learning in Collaborative Working Agents"],"prefix":"10.1109","author":[{"given":"Radu","family":"Stoican","sequence":"first","affiliation":[{"name":"University of Manchester,Manchester Centre for Robotics and AI,Manchester,United Kingdom"}]},{"given":"Angelo","family":"Cangelosi","sequence":"additional","affiliation":[{"name":"University of Manchester,Manchester Centre for Robotics and AI,Manchester,United Kingdom"}]},{"given":"Thomas H.","family":"Weisswange","sequence":"additional","affiliation":[{"name":"Honda Research Institute Europe GmbH,Offenbach,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref2","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref4","article-title":"A sur-vey of generalisation in deep reinforcement learning","author":"Kirk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967924"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04691-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102432"},{"volume-title":"Learning human-robot interactions to improve human-human collaboration","year":"2022","author":"Stoican","key":"ref13"},{"key":"ref14","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref15","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"International conference on machine learning","author":"Rakelly"},{"issue":"1","key":"ref16","first-page":"13198","article-title":"Varibad: variational bayes-adaptive deep rl via meta-learning","volume":"22","author":"Zintgraf","year":"2021","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu"},{"key":"ref18","article-title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","author":"Wang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref20","article-title":"Carl: A benchmark for contextual and adaptive reinforcement learning","author":"Benjamins","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Urlb: Unsupervised reinforcement learning benchmark","author":"Laskin","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Causalworld: A robotic manipulation benchmark for causal structure and transfer learning","author":"Ahmed","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-021-09418-4"},{"volume-title":"Learning increasingly complex skills through deep re-inforcement learning using intrinsic motivation","year":"2021","author":"Aubret","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.04.075"},{"key":"ref27","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"},{"key":"ref28","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2023,12,5]]},"location":"Mexico City, Mexico","end":{"date-parts":[[2023,12,8]]}},"container-title":["2023 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10371778\/10371788\/10371913.pdf?arnumber=10371913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T18:54:27Z","timestamp":1705085667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10371913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ssci52147.2023.10371913","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]}}}