{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T14:59:53Z","timestamp":1766847593552,"version":"3.37.3"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tg.2023.3276849","type":"journal-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T19:49:57Z","timestamp":1684266597000},"page":"384-395","source":"Crossref","is-referenced-by-count":2,"title":["Learning to Generalize With Object-Centric Agents in the Open World Survival Game <i>Crafter<\/i>"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-7536","authenticated-orcid":false,"given":"Aleksandar","family":"Stani\u0107","sequence":"first","affiliation":[{"name":"IDSIA, USI, SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2387-2090","authenticated-orcid":false,"given":"Yujin","family":"Tang","sequence":"additional","affiliation":[{"name":"Google Brain, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Ha","sequence":"additional","affiliation":[{"name":"Stability AI, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1468-6758","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[{"name":"IDSIA, USI, SUPSI, Lugano, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref3","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe","year":"2020"},{"article-title":"Neurips 2019 competition: The minerl competition on sample efficient reinforcement learning using human priors","year":"2019","author":"Guss","key":"ref4"},{"article-title":"The minerl 2020 competition on sample efficient reinforcement learning using human priors","year":"2021","author":"Guss","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463509"},{"issue":"6","key":"ref8","first-page":"2","article-title":"TORCS, the open racing car simulator","volume":"4","author":"Wymann","year":"2000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","article-title":"Behaviour suite for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Osband","year":"2020"},{"article-title":"Benchmarking the spectrum of agent capabilities","year":"2021","author":"Hafner","key":"ref11"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref12"},{"issue":"268","key":"ref13","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Raffin","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74690-4_71"},{"key":"ref16","first-page":"11525","article-title":"Object-centric learning with slot attention","volume":"33","author":"Locatello","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"On the binding problem in artificial neural networks","year":"2020","author":"Greff","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4320-5_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)80817-X"},{"key":"ref20","first-page":"6691","article-title":"Neural expectation maximization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Greff","year":"2017"},{"key":"ref21","article-title":"Relational neural expectation maximization: Unsupervised discovery of objects and their interactions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Steenkiste","year":"2018"},{"key":"ref22","first-page":"8615","article-title":"Sequential attend, infer, repeat: Generative modelling of moving objects","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Kosiorek","year":"2018"},{"key":"ref23","article-title":"R-SQAIR: Relational sequential attend, infer, repeat","volume-title":"Proc. NeurIPS PGR Workshop","author":"Stani","year":"2019"},{"key":"ref24","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Greff","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17170"},{"article-title":"Conditional object-centric learning from video","year":"2021","author":"Kipf","key":"ref26"},{"key":"ref27","article-title":"Cobra: Data-efficient model-based RL through unsupervised object discovery and curiosity-driven exploration","volume-title":"Proc. ICML Workshop Generative Model. Model-Based Reasoning Robot. AI","author":"Watters","year":"2019"},{"key":"ref28","first-page":"1439","article-title":"Entity abstraction in visual model-based reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Veerapaneni","year":"2020"},{"key":"ref29","article-title":"Contrastive learning of structured world models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf","year":"2020"},{"article-title":"Feature-attending recurrent modules for generalization in reinforcement learning","year":"2021","author":"Carvalho","key":"ref30"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref33","first-page":"3744","article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389847"},{"key":"ref36","first-page":"22574","article-title":"The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning","volume":"34","author":"Tang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"article-title":"Perceiver IO: A general architecture for structured inputs & outputs","year":"2021","author":"Jaegle","key":"ref38"},{"article-title":"Flamingo: A visual language model for few-shot learning","year":"2022","author":"Alayrac","key":"ref39"},{"article-title":"Mastering Atari with discrete world models","year":"2020","author":"Hafner","key":"ref40"},{"article-title":"Object-category aware reinforcement learning","year":"2022","author":"Yi","key":"ref41"},{"key":"ref42","article-title":"Deep reinforcement learning with relational inductive biases","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zambaldi","year":"2019"},{"article-title":"Self-supervised visual reinforcement learning with object-centric representations","year":"2020","author":"Zadaianchuk","key":"ref43"},{"key":"ref44","article-title":"Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments","volume":"90","author":"Schmidhuber","year":"1990"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490448"},{"article-title":"Steps towards self-referential learning","year":"1992","author":"Schmidhuber","key":"ref48"},{"key":"ref49","first-page":"191","article-title":"An introspective network that can learn to run its own weight change algorithm","volume-title":"Proc. IEE Int. Conf. Artif. Neural Netw.","author":"Schmidhuber","year":"1993"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2063-6_107"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298591"},{"article-title":"A modern self-referential weight matrix that learns to modify itself","year":"2022","author":"Irie","key":"ref52"},{"article-title":"Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta -$\\cdots$ hook","year":"1987","author":"Schmidhuber","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.131"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.131"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2063-6_110"},{"key":"ref57","first-page":"9355","article-title":"Linear transformers are secretly fast weight programmers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schlag","year":"2021"},{"key":"ref58","first-page":"7703","article-title":"Going beyond linear transformers with recurrent fast weight programmers","volume":"34","author":"Irie","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref59"},{"article-title":"Openai gym","year":"2016","author":"Brockman","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"article-title":"Deepmind lab","year":"2016","author":"Beattie","key":"ref62"},{"article-title":"Deepmind control suite","year":"2018","author":"Tassa","key":"ref63"},{"article-title":"Unity: A general platform for intelligent agents","year":"2018","author":"Juliani","key":"ref64"},{"article-title":"Torchcraft: A library for machine learning research on real-time strategy games","year":"2016","author":"Synnaeve","key":"ref65"},{"article-title":"Starcraft II: A new challenge for reinforcement learning","year":"2017","author":"Vinyals","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref68","first-page":"4246","article-title":"The Malmo platform for artificial intelligence experimentation","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Johnson","year":"2016"},{"key":"ref69","first-page":"203","article-title":"Retrospective analysis of the 2019 MineRL competition on sample efficient reinforcement learning","volume-title":"Proc. NeurIPS Competition Demonstration Track","author":"Milani","year":"2020"},{"article-title":"Video pretraining (VPT): Learning to act by watching unlabeled online videos","year":"2022","author":"Baker","key":"ref70"},{"article-title":"Dopamine: A research framework for deep reinforcement learning","year":"2018","author":"Castro","key":"ref71"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"article-title":"Zipfian environments for reinforcement learning","year":"2022","author":"Chan","key":"ref74"},{"article-title":"The distracting control suitea challenging benchmark for reinforcement learning from pixels","year":"2021","author":"Stone","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"article-title":"Measuring visual generalization in continuous control from pixels","year":"2020","author":"Grigsby","key":"ref77"},{"article-title":"Natural environment benchmarks for reinforcement learning","year":"2018","author":"Zhang","key":"ref78"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"article-title":"Binding via reconstruction clustering","year":"2015","author":"Greff","key":"ref80"},{"key":"ref81","first-page":"4484","article-title":"Tagger: Deep unsupervised perceptual grouping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Greff","year":"2016"},{"key":"ref82","first-page":"3225","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Eslami","year":"2016"},{"article-title":"MONet: Unsupervised scene decomposition and representation","year":"2019","author":"Burgess","key":"ref83"},{"article-title":"Genesis: Generative scene inference and sampling with object-centric latent representations","year":"2019","author":"Engelcke","key":"ref84"},{"key":"ref85","first-page":"27344","article-title":"Unsupervised object-based transition models for 3D partially observable environments","volume":"34","author":"Creswell","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref86","first-page":"7299","article-title":"Relational recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro","year":"2018"},{"article-title":"Recurrent independent mechanisms","year":"2019","author":"Goyal","key":"ref87"},{"key":"ref88","first-page":"12360","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume":"32","author":"Mott","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref89"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10559928\/10125026.pdf?arnumber=10125026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:29:15Z","timestamp":1719350955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10125026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":89,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2023.3276849","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}