{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T05:37:10Z","timestamp":1792906630818,"version":"4.5.0"},"reference-count":171,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Elite Research travel"},{"name":"The Danish Ministry for Higher Education and Science"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/tg.2019.2896986","type":"journal-article","created":{"date-parts":[[2019,2,13]],"date-time":"2019-02-13T15:31:37Z","timestamp":1550071897000},"page":"1-20","source":"Crossref","is-referenced-by-count":176,"title":["Deep Learning for Video Game Playing"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5381-5498","authenticated-orcid":false,"given":"Niels","family":"Justesen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1011-2976","authenticated-orcid":false,"given":"Philip","family":"Bontrager","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-4598","authenticated-orcid":false,"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3607-8400","authenticated-orcid":false,"given":"Sebastian","family":"Risi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"issue":"1","key":"ref3","first-page":"9","article-title":"Overview of RoboCup-98","volume":"21","author":"Asada","year":"2000","journal-title":"AI Mag."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v13i1.12922"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025696116075"},{"key":"ref6","article-title":"DeepMind lab","author":"Beattie","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref8","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bellemare","year":"2016"},{"key":"ref9","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref12","first-page":"I-115","article-title":"Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures","volume-title":"Proc. 30th Int. Conf. Int. Conf. Mach. Learn.","author":"Bergstra","year":"2013"},{"key":"ref13","first-page":"2546","article-title":"Algorithms for hyper-parameter optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bergstra","year":"2011"},{"key":"ref14","article-title":"Playing doom with SLAM-augmented deep reinforcement learning","author":"Bhatti","year":"2016"},{"key":"ref15","article-title":"Playing SNES in the retro learning environment","author":"Bhonker","year":"2017"},{"key":"ref16","article-title":"Deep apprenticeship learning for playing video games","volume-title":"Proc. Workshops 29th AAAI Conf. Artif. Intell.","author":"Bogdanovic","year":"2015"},{"key":"ref17","article-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref19","first-page":"807","article-title":"All learning is local: Multi-agent learning in global reward games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chang","year":"2003"},{"key":"ref20","article-title":"Transfer deep reinforcement learning in 3D environments: An empirical study","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chaplot","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref22","first-page":"1281","article-title":"Intrinsically motivated reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chentanez","year":"2005"},{"key":"ref23","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Christiano","year":"2017"},{"key":"ref24","first-page":"5032","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Conti","year":"2018"},{"key":"ref25","article-title":"TextWorld: A learning environment for text-based games","author":"Ct","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-021-09497-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref28","article-title":"Learning to act by predicting the future","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","year":"2017"},{"key":"ref29","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref30","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Espeholt"},{"key":"ref31","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref33","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster","year":"2017"},{"key":"ref34","article-title":"Learning to communicate to solve riddles with deep distributed recurrent q-networks","author":"Foerster","year":"2016"},{"key":"ref35","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fortunato","year":"2018"},{"key":"ref36","article-title":"Learning visual predictive models of physics for playing billiards","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fragkiadaki","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/144"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-009-9112-y"},{"key":"ref39","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref40","article-title":"Neural turing machines","author":"Graves","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490442"},{"key":"ref42","first-page":"3338","article-title":"Deep learning for real-time Atari game play using offline Monte-Carlo tree search planning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo","year":"2014"},{"key":"ref43","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Guo","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/518"},{"key":"ref45","first-page":"2450","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Advances in Neural Information Processing Systems 31","author":"Ha","year":"2018"},{"key":"ref46","first-page":"2613","article-title":"Double q-learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hasselt","year":"2010"},{"key":"ref47","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hassibi","year":"1993"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2009.2038365"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2294713"},{"key":"ref50","article-title":"Half field offense: An environment for multiagent learning and ad hoc teamwork","volume-title":"Proc. AAMAS Adaptive Learn. Agents Workshop","author":"Hausknecht","year":"2016"},{"key":"ref51","first-page":"29","article-title":"Deep recurrent q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Sequential Decis. Making Intell. Agents","author":"Hausknecht","year":"2015"},{"key":"ref52","article-title":"Deep reinforcement learning in parameterized action space","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hausknecht","year":"2016"},{"key":"ref53","article-title":"On-policy vs. off-policy updates for deep reinforcement learning","volume-title":"Proc. IJCAI Workshop: Deep Reinforcement Learn.: Frontiers Challenges","author":"Hausknecht","year":"2016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1153"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2010.5593336"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32323-2"},{"key":"ref60","article-title":"Generative agents for player decision modeling in games","volume-title":"Proc. 9th Int. Conf. Found. Digit. Games","author":"Holmgrd","year":"2014"},{"key":"ref61","article-title":"Distributed prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Horgan","year":"2018"},{"key":"ref62","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and $< $ 0.5 MB model size","author":"Iandola","year":"2016"},{"key":"ref63","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jaderberg","year":"2017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2016.2535416"},{"key":"ref65","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":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31204-0_38"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071210"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080430"},{"key":"ref69","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","volume-title":"Proc. NeurIPS Workshop Deep Reinforcement Learn.","author":"Justesen","year":"2018"},{"key":"ref70","first-page":"1809","article-title":"Schema networks: Zero-shot transfer with a generative causal model of intuitive physics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kansky","year":"2017"},{"key":"ref71","article-title":"Beating Atari with natural language guided reinforcement learning","author":"Kaplan","year":"2017"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071303"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080433"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463509"},{"key":"ref77","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kulkarni","year":"2016"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2017.7969556"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-007-9079-x"},{"key":"ref84","first-page":"329","article-title":"Exploiting open-endedness to solve problems through the search for novelty","volume-title":"Proc. 11th Int. Conf. Artif. Life","author":"Lehman","year":"2008"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.65109\/QMSU8421"},{"key":"ref86","first-page":"430","article-title":"Learning physical intuition of block towers by example","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lerer","year":"2016"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"key":"ref88","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap","year":"2016"},{"key":"ref89","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1993"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2006.1597057"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref92","article-title":"Teacher-student curriculum learning","volume-title":"Proc. Deep Reinforcement Learn. Symp.","author":"Matiisen","year":"2017"},{"key":"ref93","first-page":"155","article-title":"Computational intelligence in games","volume-title":"Computational Intelligence: Principles and Practice","author":"Miikkulainen","year":"2006"},{"key":"ref94","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"ref95","article-title":"Learning to navigate in complex environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mirowski","year":"2016"},{"key":"ref96","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref97","article-title":"Playing Atari with deep reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst., Deep Learn. Workshop","author":"Mnih","year":"2013"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref99","article-title":"Learning and game AI","volume-title":"Dagstuhl Follow-Ups","volume":"6","author":"Muoz-Avila","year":"2013"},{"key":"ref100","article-title":"Massively parallel methods for deep reinforcement learning","author":"Nair","year":"2015"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d15-1001"},{"key":"ref102","first-page":"2790","article-title":"Control of memory, active perception, and action in Minecraft","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Oh","year":"2016"},{"key":"ref103","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oh","year":"2015"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v9i1.12681"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.entcom.2012.10.001"},{"key":"ref106","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Osband","year":"2016"},{"key":"ref107","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref108","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Parisotto","year":"2016"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2184109"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref111","article-title":"Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games","author":"Peng","year":"2017"},{"key":"ref112","article-title":"Observe and look further: Achieving consistent performance on Atari","author":"Pohlen","year":"2018"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080444"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v8i1.12502"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2494596"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref117","doi-asserted-by":"crossref","first-page":"45","DOI":"10.7551\/mitpress\/5236.003.0018","article-title":"A general framework for parallel distributed processing","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition","volume":"1","author":"Rumelhart","year":"1986"},{"key":"ref118","volume-title":"On-Line Q-Learning Using Connectionist Systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref119","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rusu","year":"2016"},{"key":"ref120","article-title":"Progressive neural networks","author":"Rusu","year":"2016"},{"key":"ref121","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633610"},{"key":"ref123","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul","year":"2016"},{"key":"ref124","article-title":"Measuring intelligence through games","author":"Schaul","year":"2011"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1404.7828"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2011.6032024"},{"key":"ref128","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref129","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42716-4"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633634"},{"key":"ref132","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shelhamer","year":"2016"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref134","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860436"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860439"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2005.856210"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45603-1_22"},{"key":"ref139","first-page":"145","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","volume-title":"Proc. 11th Annu. Conf. Genetic Evol. Comput.","author":"Such"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref141","article-title":"TStarBots: Defeating the cheating level builtin AI in StarCraft II in the full game","author":"Sun","year":"2018"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref143","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"99","author":"Sutton","year":"1999"},{"key":"ref144","volume-title":"Emergence in Games","author":"Sweetser","year":"2008"},{"key":"ref145","article-title":"TorchCraft: A library for machine learning research on real-time strategy games","author":"Synnaeve","year":"2016"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2018.8426160"},{"key":"ref149","first-page":"4497","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Teh","year":"2017"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref151","first-page":"2656","article-title":"ELF: An extensive, lightweight and flexible research platform for real-time strategy games","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tian","year":"2017"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"3","key":"ref153","first-page":"30","article-title":"Ontogenetic and phylogenetic reinforcement learning","volume":"23","author":"Togelius","year":"2009","journal-title":"Knstliche Intell."},{"key":"ref154","article-title":"Episodic exploration for deep deterministic policies: An application to StarCraft micromanagement tasks","author":"Usunier","year":"2016"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref156","first-page":"5396","article-title":"Hybrid reward architecture for reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Van Seijen","year":"2017"},{"key":"ref157","article-title":"Starcraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205517"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v12i1.12862"},{"key":"ref160","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2017"},{"key":"ref161","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700600202"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref166","first-page":"5285","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu","year":"2017"},{"key":"ref167","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu","year":"2017"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-83347-2_10"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2014.2339221"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63519-4"},{"key":"ref172","article-title":"A deep compositional framework for human-like language acquisition in virtual environment","author":"Yu","year":"2017"},{"key":"ref173","first-page":"3562","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","volume-title":"Advances in Neural Information Processing Systems 31","author":"Zahavy","year":"2018"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/9039767\/08632747.pdf?arnumber=8632747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T05:14:31Z","timestamp":1792905271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8632747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":171,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2019.2896986","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}