{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:28:52Z","timestamp":1781584132974,"version":"3.54.5"},"reference-count":194,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Cognizant Technology Solutions through the Internet of Swarms Project"},{"name":"Rijksdienst voor Ondernemend Nederland under PPS O&I"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2023.3264540","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T18:04:39Z","timestamp":1683050679000},"page":"11939-11957","source":"Crossref","is-referenced-by-count":68,"title":["Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8225-6410","authenticated-orcid":false,"given":"Amjad Yousef","family":"Majid","sequence":"first","affiliation":[{"name":"Department of Microelectronics, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serge","family":"Saaybi","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Francois-Lavet","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7443-7641","authenticated-orcid":false,"given":"R. Venkatesha","family":"Prasad","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0106-8117","authenticated-orcid":false,"given":"Chris","family":"Verhoeven","sequence":"additional","affiliation":[{"name":"Department of Microelectronics, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-05094-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0241-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2018.03.011"},{"key":"ref7","article-title":"On-line Q-learning using connectionist systems","author":"Rummery","year":"1994"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849837"},{"key":"ref9","article-title":"Playing Atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref10","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. NeurIPS","author":"Sutton"},{"key":"ref11","article-title":"Efficient parallel methods for deep reinforcement learning","volume-title":"arXiv:1705.04862","author":"Clemente","year":"2017"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref13","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","article-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1993"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43505-2_44"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100694"},{"key":"ref20","first-page":"149","article-title":"Similarities and differences between policy gradient methods and evolution strategies","volume-title":"Proc. ESANN","author":"Heidrich-Meisner"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87700-4_43"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2009.04.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553426"},{"key":"ref24","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","volume-title":"arXiv:1703.03864","author":"Salimans","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/197"},{"key":"ref26","volume-title":"Evolutionsstrategie Optimierung technischer Systeme nach Prinzipien der biologischen Evolution","author":"Rechenberg","year":"1973"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04832-8"},{"key":"ref28","article-title":"An introduction to genetic algorithms and evolution strategies","author":"Dianati","year":"2002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-0348-5927-1_5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1996.542381"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref33","article-title":"The CMA evolution strategy: A tutorial","volume-title":"arXiv:1604.00772","author":"Hansen","year":"2016"},{"issue":"1","key":"ref34","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"Wierstra","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","volume-title":"Reinforcement Learning With Selective Perception and Hidden State","author":"McCallum","year":"1996"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11662-4_11"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11478"},{"key":"ref38","article-title":"On improving deep reinforcement learning for POMDPs","volume-title":"arXiv:1704.07978","author":"Zhu","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-008-0388-7"},{"key":"ref40","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"arXiv:1507.06527","author":"Hausknecht","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2003.1299414"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.4650"},{"key":"ref43","article-title":"A simple neural attentive meta-learner","volume-title":"arXiv:1707.03141","author":"Mishra","year":"2017"},{"key":"ref44","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"arXiv:1803.11347","author":"Nagabandi","year":"2018"},{"key":"ref45","first-page":"1","article-title":"A meta-MDP approach to exploration for lifelong reinforcement learning","volume-title":"Proc. NeurIPS","author":"Garcia"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.trip.2019.100020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref53","article-title":"Autonomous air traffic controller: A deep multi-agent reinforcement learning approach","volume-title":"arXiv:1905.01303","author":"Brittain","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/545056.545078"},{"key":"ref55","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_11"},{"key":"ref57","article-title":"How to discount deep reinforcement learning: Towards new dynamic strategies","volume-title":"arXiv:1512.02011","author":"Fran\u00e7ois-Lavet","year":"2015"},{"key":"ref58","article-title":"Massively parallel methods for deep reinforcement learning","volume-title":"arXiv:1507.04296","author":"Nair","year":"2015"},{"key":"ref59","article-title":"Distributed prioritized experience replay","volume-title":"arXiv:1803.00933","author":"Horgan","year":"2018"},{"key":"ref60","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. ICML","author":"Espeholt"},{"key":"ref61","article-title":"SEED RL: Scalable and efficient deep-RL with accelerated central inference","volume-title":"arXiv:1910.06591","author":"Espeholt","year":"2019"},{"key":"ref62","first-page":"1","article-title":"Parallel reinforcement learning with linear function approximation","volume-title":"Proc. 6th Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Grounds"},{"key":"ref63","first-page":"1","article-title":"Large scale distributed deep networks","volume-title":"Proc. NIPS","author":"Dean"},{"key":"ref64","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","volume-title":"arXiv:1611.06256","author":"Babaeizadeh","year":"2016"},{"key":"ref65","article-title":"Emergence of locomotion behaviours in rich environments","volume-title":"arXiv:1707.02286","author":"Heess","year":"2017"},{"key":"ref66","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref67","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proc. ICLR","author":"Kapturowski"},{"key":"ref68","first-page":"1","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume-title":"Proc. NeurIPS","author":"Conti"},{"key":"ref69","article-title":"Learning in sparse rewards settings through quality-diversity algorithms","volume-title":"arXiv:2203.01027","author":"Paolo","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014352"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/172"},{"key":"ref72","article-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration","volume-title":"arXiv:2202.04628","author":"Rengarajan","year":"2022"},{"key":"ref73","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","volume-title":"arXiv:2109.06668","author":"Yang","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref75","article-title":"Dealing with sparse rewards in continuous control robotics via heavy-tailed policies","volume-title":"arXiv:2206.05652","author":"Chakraborty","year":"2022"},{"key":"ref76","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. NeurIPS","volume":"30","author":"Andrychowicz"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref78","article-title":"A tutorial on Thompson sampling","volume-title":"arXiv:1707.02038","author":"Russo","year":"2017"},{"key":"ref79","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","volume-title":"arXiv:1703.01732","author":"Achiam","year":"2017"},{"key":"ref80","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. ICML","author":"Pathak"},{"key":"ref81","article-title":"EMI: Exploration with mutual information","volume-title":"arXiv:1810.01176","author":"Kim","year":"2018"},{"key":"ref82","first-page":"1","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bellemare"},{"key":"ref83","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski"},{"key":"ref84","first-page":"1","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. NIPS","author":"Tang"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2056368"},{"key":"ref88","first-page":"1","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. NIPS","author":"Houthooft"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref90","article-title":"Exploration by random network distillation","volume-title":"arXiv:1810.12894","author":"Burda","year":"2018"},{"key":"ref91","first-page":"5779","article-title":"Model-based active exploration","volume-title":"Proc. ICML","author":"Shyam"},{"key":"ref92","article-title":"Deep exploration via bootstrapped DQN","volume-title":"arXiv:1602.04621","author":"Osband","year":"2016"},{"key":"ref93","article-title":"UCB exploration via Q-ensembles","volume-title":"arXiv:1706.01502","author":"Chen","year":"2017"},{"key":"ref94","article-title":"Episodic curiosity through reachability","volume-title":"arXiv:1810.02274","author":"Savinov","year":"2018"},{"key":"ref95","article-title":"Go-explore: A new approach for hard-exploration problems","volume-title":"arXiv:1901.10995","author":"Ecoffet","year":"2020"},{"key":"ref96","article-title":"Never give up: Learning directed exploration strategies","volume-title":"arXiv:2002.06038","author":"Badia","year":"2020"},{"key":"ref97","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia"},{"key":"ref98","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"arXiv:1802.06070","author":"Eysenbach","year":"2018"},{"key":"ref99","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"arXiv:1907.01657","author":"Sharma","year":"2019"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.3934\/era.2021075"},{"key":"ref101","first-page":"1","article-title":"Improved techniques for training GANs","volume-title":"Proc. NeurIPS","author":"Salimans"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(88)90027-9"},{"key":"ref103","first-page":"970","article-title":"Structured evolution with compact architectures for scalable policy optimization","volume-title":"Proc. ICML","author":"Choromanski"},{"key":"ref104","first-page":"4264","article-title":"Guided evolutionary strategies: Augmenting random search with surrogate gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maheswaranathan"},{"key":"ref105","article-title":"Improving gradient estimation in evolutionary strategies with past descent directions","volume-title":"arXiv:1910.05268","author":"Meier","year":"2019"},{"key":"ref106","first-page":"1","article-title":"From complexity to simplicity: Adaptive es-active subspaces for blackbox optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Choromanski"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/205"},{"key":"ref108","article-title":"A novel evolution strategy with directional Gaussian smoothing for blackbox optimization","volume-title":"arXiv:2002.03001","author":"Zhang"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1770-5_3"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00040"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108624"},{"key":"ref112","first-page":"3836","article-title":"The uncertainty Bellman equation and exploration","volume-title":"Proc. ICML","author":"O\u2019Donoghue"},{"key":"ref113","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman"},{"key":"ref114","first-page":"1","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref116","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. ICML","author":"Santoro"},{"key":"ref117","article-title":"Rl\u2082: Fast reinforcement learning via slow reinforcement learning","volume-title":"arXiv:1611.02779","author":"Duan","year":"2016"},{"key":"ref118","article-title":"Learning to reinforcement learn","volume-title":"arXiv:1611.05763","author":"Wang","year":"2016"},{"key":"ref119","article-title":"Learning to reinforcement learn for neural architecture search","volume-title":"arXiv:1911.03769","author":"Robles","year":"2019"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10004-4"},{"key":"ref121","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. ICML","author":"Finn"},{"key":"ref122","article-title":"On first-order meta-learning algorithms","volume-title":"arXiv:1803.02999","author":"Nichol","year":"2018"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321876"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/2908812.2908838"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1162\/isal_a_00414"},{"key":"ref127","article-title":"Meta-learning in neural networks: A survey","volume-title":"arXiv:2004.05439","author":"Hospedales","year":"2020"},{"key":"ref128","article-title":"ES-MAML: Simple hessian-free meta learning","volume-title":"arXiv:1910.01215","author":"Song","year":"2019"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341571"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3160173"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3112718"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196540"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2976000"},{"key":"ref135","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","volume-title":"arXiv:1707.09183","author":"Hernandez-Leal","year":"2017"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref137","volume-title":"Deep reinforcement learning variants of multi-agent learning algorithms","author":"Castaneda","year":"2016"},{"key":"ref138","article-title":"Lenient multi-agent deep reinforcement learning","volume-title":"arXiv:1707.04402","author":"Palmer","year":"2017"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139357"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref141","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","volume-title":"arXiv:2011.00583","author":"Yang","year":"2020"},{"key":"ref142","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"arXiv:1706.05296","author":"Sunehag","year":"2017"},{"key":"ref143","first-page":"1","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref145","article-title":"A new framework for multi-agent reinforcement learning\u2014Centralized training and exploration with decentralized execution via policy distillation","volume-title":"arXiv:1910.09152","author":"Chen","year":"2019"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref147","first-page":"1","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume-title":"Proc. ICML","author":"Lauer"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref149","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Foerster"},{"key":"ref150","article-title":"A review of cooperative multi-agent deep reinforcement learning","volume-title":"arXiv:1908.03963","author":"OroojlooyJadid","year":"2019"},{"key":"ref151","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"arXiv:1706.02275","author":"Lowe","year":"2017"},{"key":"ref152","article-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","volume-title":"arXiv:1710.00336","author":"Chu","year":"2017"},{"key":"ref153","article-title":"Multi-agent actor-critic with generative cooperative policy network","volume-title":"arXiv:1810.09206","author":"Ryu","year":"2018"},{"key":"ref154","article-title":"Modelling the dynamic joint policy of teammates with attention multi-agent DDPG","volume-title":"arXiv:1811.07029","author":"Mao","year":"2018"},{"key":"ref155","article-title":"R-MADDPG for partially observable environments and limited communication","volume-title":"arXiv:2002.06684","author":"Wang","year":"2020"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/SMCIA.2008.5045926"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45173-0_29"},{"key":"ref158","article-title":"Learning to communicate to solve riddles with deep distributed recurrent Q-networks","volume-title":"arXiv:1602.02672","author":"Foerster","year":"2016"},{"key":"ref159","article-title":"Learning multiagent communication with backpropagation","volume-title":"arXiv:1605.07736","author":"Sukhbaatar","year":"2016"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09938-y"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-018-0483-5"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2019.8790103"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341777"},{"key":"ref166","article-title":"A framework for learning predator-prey agents from simulation to real world","volume-title":"arXiv:2010.15792","author":"Chen","year":"2020"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-53956-6_57"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3426826.3426835"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628677"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.3390\/app11062856"},{"key":"ref171","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","volume-title":"arXiv:1712.06567","author":"Petroski Such","year":"2017"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref173","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","volume-title":"arXiv:1810.01222","author":"Pourchot","year":"2018"},{"key":"ref174","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. ICML","author":"Fujimoto"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41188-6_7"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0266841"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(97)00372-X"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105937"},{"key":"ref180","article-title":"Evolutionary reinforcement learning","volume-title":"arXiv:1805.07917","author":"Khadka","year":"2018"},{"key":"ref181","first-page":"56","article-title":"A study of the impact of evolutionary strategies on performance of reinforcement learning autonomous agents","volume-title":"Proc. ICAS","author":"Shopov"},{"key":"ref182","first-page":"1","article-title":"Evolved policy gradients","volume-title":"Proc. NeurIPS","author":"Houthooft"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01702-7"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2240"},{"key":"ref185","article-title":"ES-ENAS: Combining evolution strategies with neural architecture search at no extra cost for reinforcement learning","volume-title":"arXiv:2101.07415","author":"Song","year":"2021"},{"key":"ref186","article-title":"Learning synthetic environments for reinforcement learning with evolution strategies","volume-title":"arXiv:2101.09721","author":"Ferreira","year":"2021"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37140-0_28"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889738"},{"key":"ref189","first-page":"1101","article-title":"Deep dynamics models for learning dexterous manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nagabandi"},{"key":"ref190","article-title":"Sample-efficient reinforcement learning in robotic table tennis","volume-title":"arXiv:2011.03275","author":"Tebbe","year":"2020"},{"key":"ref191","article-title":"Importance mixing: Improving sample reuse in evolutionary policy search methods","volume-title":"arXiv:1808.05832","author":"Pourchot","year":"2018"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.011"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569976"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10114063.pdf?arnumber=10114063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T14:14:35Z","timestamp":1725459275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":194,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3264540","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.14679504","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.14679504.v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.14679504.v1","asserted-by":"object"}]},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}