Human-level control through deep reinforcement learning
The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-networ…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In previous studies, the agents are assumed to act based on simple and heuristic policy functions, and learned in isolated and restricted environments [1][2][3][4][5][6].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [1]
In the citing paper
“This technique was developed in 2013 with Google Deep Mind [55].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [55]
In the citing paper
“Whereas previous reinforcement-learning algorithms often rely only on task-specific learning signals9,10, Dreamer rests predominantly on the unsupervised objective of its world model.”
From Mastering diverse control tasks through world models (2025) · cites this paper as [9]
In the citing paper
“Traditional RL such as AlphaGo Zero and the DQN series (Silver et al., 2017; Mnih et al., 2015; Yue et al., 2023) can continuously improve the performance of a policy in environments like Go and Atari games without an explicit upper bound .”
From Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (2025) · cites this paper as Mnih et al., 2015
In the citing paper
“Unlike previous reinforcement learning algorithms that often rely only on task-specific learning signals 7,8 , Dreamer rests predominantly on the unsupervised objective of its world model.”
From Mastering Diverse Domains through World Models (2023) · cites this paper as [7]
24 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“We use one particularly successful architecture, the deep convolutional network 17 , which uses hierarchical layers of tiled convolutional filters tomimictheeffectsofreceptivefields—inspiredbyHubelandWiesel’s seminalworkonfeedforwardprocessinginearlyvisualcortex 18 —thereby…”
Method(2008) · Journal of Machine Learning Research · Cited by 33,051
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
(2010) · International Conference on Machine Learning · Cited by 13,995
A neural substrate of prediction and reward
Schultz, W., Dayan, P., & Montague, P. R. (1997) · Science · doi:10.1126/science.275.5306.1593 · Cited by 9,388 · cited 1×
“…4,5 , the former evidenced by a wealth of neural data revealingnotableparallelsbetweenthephasicsignalsemittedbydopa-minergicneuronsandtemporaldifferencereinforcementlearning algorithms 3 .”
BackgroundLearning Deep Architectures for AI
Bengio, Y. (2009) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000006 · Cited by 9,239 · cited 2×
“Notably, recent advances in deep neural networks 9–11 , in which several layers of nodes areused to buildup progressivelymore abstractrepresentations of the data, have made it possible for artificial neural networks to learn concepts such as object categories directly from raw sensory data.”
BackgroundWatkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Cited by
Items 1,201–1,300 of 1,418
Sim-to-Real Transfer with Neural-Augmented Robot Simulation
(2018) · HAL · Cited by 63
Computing schizophrenia: ethical challenges for machine learning in psychiatry
Starke, G., De Clercq, E., Borgwardt, S., & Elger, B. S. (2021) · Psychological Medicine · doi:10.1017/s0033291720001683 · Cited by 62
“Finally, reinforcement learning denotes ML programs that optimize their interaction with an environment by trying to maximize reward over time (Mnih et al., 2015).”
BackgroundVariance Reduction for Reinforcement Learning in Input-Driven Environments
Mao, H., Venkatakrishnan, S. B., Schwarzkopf, M., & Alizadeh, M. (2018) · arXiv · doi:10.48550/arxiv.1807.02264 · Cited by 62
“…learning (RL) has emerged as a powerful approach to sequential decision-making problems, achieving impressive results in domains such as game playing (Mnih et al., 2015; Silver et al., 2017), robotics (Levine et al., 2016), and continuous control (Schulman et al., 2015a; Lillicrap et al., 2015).”
BackgroundPOET: open-ended coevolution of environments and their optimized solutions
Wang, R., Lehman, J., Clune, J., & Stanley, K. O. (2019) · Proceedings of the Genetic and Evolutionary Computation Conference · doi:10.1145/3321707.3321799 · Cited by 61
“Policy gradient methods [50], Q-learning [41], genetic algorithms, other variants of ES, diversity-promoting algorithms such as QD [9, 37, 42, 45] and NS [38], including NS-/NSRA-ES [8], and many other such algorithms are all viable alternatives.”
BackgroundMethodPflueger, M., Agha, A., & Sukhatme, G. S. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2895892 · Cited by 60
Understanding World or Predicting Future? A Comprehensive Survey of World Models
Ding, J., Zhang, Y., Shang, Y., Zhang, Y., Zong, Z., Feng, J., Yuan, Y., Su, H., Li, N., Sukiennik, N., et al. (2026) · ACM Computing Surveys · doi:10.1145/3746449 · Cited by 169
Explainable Reinforcement Learning through a Causal Lens
Madumal, P., Miller, T., Sonenberg, L., & Vetere, F. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i03.5631 · Cited by 58
Measuring the Reliability of Reinforcement Learning Algorithms
Chan, S. C. Y., Fishman, S., Canny, J., Korattikara, A., & Guadarrama, S. (2019) · arXiv · doi:10.48550/arxiv.1912.05663 · Cited by 57
“The RL algorithms are: DQN (Mnih et al., 2015), Implicit Quantile (IQN) (Dabney et al., 2018), C51 (Bellemare et al., 2017), and a variant of Rainbow implementing the three most important components (Hessel & Modayil, 2018).”
MethodModel-based reinforcement learning for ultrasound-driven autonomous microrobots
Medany, M., Piglia, L., Achenbach, L., Mukkavilli, S. K., & Ahmed, D. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01054-2 · Cited by 56
“Although RL has the potential to surpass human capabilities in tasks like object manipulation and strategic gameplay 41,42 , its reliance on extensive interactions for stable training introduces unique challenges for microrobots, as the experimental conditions are highly uncontrolled and variable.”
Open-Ended Learning Leads to Generally Capable Agents
Open Ended Learning Team, Stooke, A., Mahajan, A., Barros, C., Deck, C., Bauer, J., Sygnowski, J., Trebacz, M., Jaderberg, M., Mathieu, M., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.12808 · Cited by 56
“Correspondence to jaderberg@deepmind.com able and general reinforcement learning algorithms to train these networks, has resulted in agents that can outperform humans on the complex simulated games they were trained on (Mnih et al., 2015).”
BackgroundHand Gesture Recognition Using EMG-IMU Signals and Deep Q-Networks
Vásconez, J. P., Barona López, L. I., Valdivieso Caraguay, Á. L., & Benalcázar, M. E. (2022) · Sensors · doi:10.3390/s22249613 · Cited by 55
“This helps to remove correlations with the target [26,28].”
BackgroundMethodInfluentialYuan, W., Hang, K., Kragic, D., Wang, M. Y., & Stork, J. A. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.06.007 · Cited by 54
Hybrid Network Model for “Deep Learning” of Chemical Data: Application to Antimicrobial Peptides
Schneider, P., Müller, A. T., Gabernet, G., Button, A. L., Posselt, G., Wessler, S., Hiss, J. A., & Schneider, G. (2017) · Molecular Informatics · doi:10.1002/minf.201600011 · Cited by 52
Learning Continuous Control Actions for Robotic Grasping with Reinforcement Learning
Shahid, A. A., Roveda, L., Piga, D., & Braghin, F. (2020) · 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC) · doi:10.1109/smc42975.2020.9282951 · Cited by 54
“Considering ii), RL methods have been successfully applied in a wide variety of contexts, ranging from playing games [5] to robotic locomotion [6].”
MethodLocal and global explanations of agent behavior: Integrating strategy summaries with saliency maps
Huber, T., Weitz, K., André, E., & Amir, O. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103571 · Cited by 53
“Here, too, we expect similar effects in terms of participants’ explanation satisfaction in each task.”
BackgroundMethodResultInfluentialDeep Reinforcement Learning for Syntactic Error Repair in Student Programs
Gupta, R., Kanade, A., & Shevade, S. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301930 · Cited by 54
“Through deep reinforcement learning, agents have been trained to play visual and text-based games at expert levels (Mnih et al. 2015; Narasimhan, Kulkarni, and Barzi-lay 2015; Wu and Tian 2016).”
BackgroundAn Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey
Aubret, A., Matignon, L., & Hassas, S. (2023) · Entropy · doi:10.3390/e25020327 · Cited by 52
“Thus, the agent never finds rewards and cannot learn a good policy with respect to the task [3].”
BackgroundMethodInfluentialHierarchical Query Graph Generation for Complex Question Answering over Knowledge Graph
Qiu, Y., Zhang, K., Wang, Y., Jin, X., Bai, L., Guan, S., & Cheng, X. (2020) · Proceedings of the 29th ACM International Conference on Information & Knowledge Management · doi:10.1145/3340531.3411888 · Cited by 52
“Compared with typical flat RL methods such as DQN [28] and the REINFORCE algorithm [43], our strategy helps alleviate the credit assignment problem arising from long decision trajectories.”
MethodFinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance
Liu, X.-Y., Yang, H., Chen, Q., Zhang, R., Yang, L., Xiao, B., & Wang, C. (2025) · doi:10.2139/ssrn.3737859 · Cited by 53
“FinRL library includes fine-tuned standard DRL algorithms, namely, DQN [29][34], DDPG [29], Multi-Agent DDPG [30], PPO [40], SAC [18], A2C [33] and TD3 [11].”
Zhang, Z., Yao, Y., Zhang, A., Tang, X., Ma, X., He, Z., Wang, Y., Gerstein, M., Wang, R., Liu, G., et al. (2025) · ACM Computing Surveys · doi:10.1145/3719341 · Cited by 51
Modified DDPG car-following model with a real-world human driving experience with CARLA simulator
Li, D., & Okhrin, O. (2023) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2022.103987 · Cited by 51
NNWarp: Neural Network-based Nonlinear Deformation
Luo, R., Shao, T., Wang, H., Xu, W., Chen, X., Zhou, K., & Yang, Y. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2881451 · Cited by 50
“NNs provide a convenient approach for further improving the learning effects [37].”
BackgroundGeneration of Synthetic Electronic Medical Record Text
Guan, J., Li, R., Yu, S., & Zhang, X. (2018) · 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621223 · Cited by 49
(2019) · International Conference on Machine Learning · Cited by 49
A Deep Reinforcement Learning Method for Mobile Robot Collision Avoidance based on Double DQN
Xue, X., Li, Z., Zhang, D., & Yan, Y. (2019) · 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2019.8781522 · Cited by 48
“This work has led to an application-based intelligent collision avoidance algorithm based on Deep Double Q-Learning.”
MethodDehghani, M., Tay, Y., Gritsenko, A. A., Zhao, Z., Houlsby, N., Diaz, F., Metzler, D., & Vinyals, O. (2021) · arXiv · doi:10.48550/arxiv.2107.07002 · Cited by 48
“For example, some papers use a non-default value for the skipframe parameter 9 in their baseline models [Mnih et al., 2015].”
BackgroundMethodIs it time to get rid of black boxes and cultivate trust in AI?
Gastounioti, A., & Kontos, D. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020200088 · Cited by 47
ADT: Time series anomaly detection for cyber-physical systems via deep reinforcement learning
Yang, X., Howley, E., & Schukat, M. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103825 · Cited by 47
Advancing Fusion with Machine Learning Research Needs Workshop Report
Humphreys, D., Kupresanin, A., Boyer, M. D., Canik, J., Chang, C. S., Cyr, E. C., Granetz, R., Hittinger, J., Kolemen, E., Lawrence, E., et al. (2020) · Journal of Fusion Energy · doi:10.1007/s10894-020-00258-1 · Cited by 47
Efficient Client Contribution Evaluation for Horizontal Federated Learning
Zhao, J., Zhu, X., Wang, J., & Xiao, J. (2021) · ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp39728.2021.9413377 · Cited by 50
Observational Learning by Reinforcement Learning
Borsa, D., Piot, B., Munos, R., & Pietquin, O. (2017) · arXiv · doi:10.48550/arxiv.1706.06617 · Cited by 47
Learning Arbitrary-Goal Fabric Folding with One Hour of Real Robot Experience
Lee, R., Ward, D., Cosgun, A., Dasagi, V., Corke, P., & Leitner, J. (2020) · arXiv · doi:10.48550/arxiv.2010.03209 · Cited by 47
Observational Learning by Reinforcement Learning
Borsa, D., Heess, N., Piot, B., Liu, S., Hasenclever, L., Munos, R., & Pietquin, O. (2019) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/nqzd5621 · Cited by 47
Real-Time Reinforcement Learning Optimized Energy Management for a 48V Mild Hybrid Electric Vehicle
Xu, B., Malmir, F., Rathod, D., & Filipi, Z. (2019) · SAE Technical Paper Series · doi:10.4271/2019-01-1208 · Cited by 47
Curiosity-Driven Experience Prioritization via Density Estimation
Zhao, R., & Tresp, V. (2019) · arXiv · doi:10.48550/arxiv.1902.08039 · Cited by 47
“Experience replay was proposed by Lin [27] and became popular due to the success of DQN [29].”
BackgroundMethodInfluentialArtificial intelligence in radiotherapy
Li, G., Wu, X., & Ma, X. (2022) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2022.08.005 · Cited by 46
Witman, M., Gidon, D., Graves, D. B., Smit, B., & Mesbah, A. (2019) · Plasma Sources Science and Technology · doi:10.1088/1361-6595/ab3c15 · Cited by 46
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
Guss, W. H., Codel, C., Hofmann, K., Houghton, B., Kuno, N., Milani, S., Mohanty, S., Liebana, D. P., Salakhutdinov, R., Topin, N., et al. (2019) · arXiv · doi:10.48550/arxiv.1904.10079 · Cited by 46
“In the presented comparison, the DQN is an implementation of Double Dueling DQN and Behavioral Cloning is a supervised learning method trained on expert trajectories.”
MethodInfluentialDayDreamer: World Models for Physical Robot Learning
Wu, P., Escontrela, A., Hafner, D., Goldberg, K., & Abbeel, P. (2022) · arXiv · doi:10.48550/arxiv.2206.14176 · Cited by 76
“To compute the λ -returns, we use a slowly updated copy of the critic network as common in the literature (Mnih et al., 2015; Lillicrap et al., 2015).”
MethodInfluentialA Survey of Reinforcement Learning from Human Feedback
Kaufmann, T., Weng, P., Bengs, V., & Hüllermeier, E. (2023) · arXiv · doi:10.48550/arxiv.2312.14925 · Cited by 43
Huber, L. S., Geirhos, R., & Wichmann, F. A. (2023) · Journal of Vision · doi:10.1167/jov.23.7.4 · Cited by 42
“Third, an exciting possibility is that humans enlarge their initial dataset provided through external input by creatively using already encountered instances to create new instances during offline states—a concept similar to what in reinforcement learning is called experience replay (e.g., see O’Neill, Pleydell-Bouver…”
BackgroundButz, M. V. (2021) · KI - Künstliche Intelligenz · doi:10.1007/s13218-021-00705-x · Cited by 42
Quantitative Trading on Stock Market Based on Deep Reinforcement Learning
WU, J., WANG, C., XIONG, L., & SUN, H. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851831 · Cited by 42
Toward Smart Security Enhancement of Federated Learning Networks
Tan, J., Liang, Y.-C., Luong, N. C., & Niyato, D. (2021) · IEEE Network · doi:10.1109/mnet.011.2000379 · Cited by 42
“The interested readers can refer to [1] and [4] for more details about DRL.”
BackgroundMethodMulti-modality Sensor Data Classification with Selective Attention
Zhang, X., Yao, L., Huang, C., Wang, S., Tan, M., Long, G., & Wang, C. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/432 · Cited by 41
An Interpretable Planning Bot for Pancreas Stereotactic Body Radiation Therapy
Zhang, J., Wang, C., Sheng, Y., Palta, M., Czito, B., Willett, C., Zhang, J., Jensen, P. J., Yin, F.-F., Wu, Q., et al. (2021) · International Journal of Radiation Oncology*Biology*Physics · doi:10.1016/j.ijrobp.2020.10.019 · Cited by 41
A Survey of Exploration Methods in Reinforcement Learning
Amin, S., Gomrokchi, M., Satija, H., van Hoof, H., & Precup, D. (2021) · arXiv · doi:10.48550/arxiv.2109.00157 · Cited by 41
“They evaluate their proposed method in 14 Arcade Learning Environments (ALE) against Boltzmann, DQN and Thompson sampling methods.”
MethodInfluentialWhy Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
Ghosh, D., Rahme, J., Kumar, A., Zhang, A., Adams, R. P., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2107.06277 · Cited by 41
Reinforcement learning and artificial agency
Butlin, P. (2024) · Mind & Language · doi:10.1111/mila.12458 · Cited by 40
Human-in-the-loop reinforcement learning in continuous-action space
Luo, B., Wu, Z., Zhou, F., & Wang, B.-C. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3289315 · Cited by 41
Minimalistic Attacks: How Little It Takes to Fool Deep Reinforcement Learning Policies
Qu, X., Sun, Z., Ong, Y.-S., Gupta, A., & Wei, P. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.2974509 · Cited by 40
“The network structure is taken from [46], and is kept the same for all the four RL algorithms.”
MethodWang, Z., Li, H.-X., & Chen, C. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2927320 · Cited by 39
“The (cid:9) -greedy technique is usually employed in value function-based RL algorithms such as the classical Q-learning [4] and the state-of-the-art deep Q-network [12].”
BackgroundMethodQuantum adiabatic algorithm design using reinforcement learning
Lin, J., Lai, Z. Y., & Li, X. (2020) · Physical Review A · doi:10.1103/physreva.101.052327 · Cited by 39
SAGE: Self-evolving Agents with Reflective and Memory-augmented Abilities
Liang, X., Tao, M., Xia, Y., Wang, J., Li, K., Wang, Y., He, Y., Yang, J., Shi, T., Wang, Y., et al. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130470 · Cited by 39
Kunpeng, Y., Shan, H., Sun, T., Hu, R., Wu, Y., Yu, L., Zhang, Z., & Quek, T. Q. S. (2021) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2021.3073744 · Cited by 39
Sentiment and Knowledge Based Algorithmic Trading with Deep Reinforcement Learning
Nan, A., Perumal, A., & Zaiane, O. R. (2020) · arXiv · doi:10.48550/arxiv.2001.09403 · Cited by 39
Wang, H., Tan, A. H., & Nejat, G. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3412638 · Cited by 40
“Task-specific feature extraction has been shown to enhance policy learning in robot navigation [33].”
BackgroundKreutzer, J., Uyheng, J., & Riezler, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1165 · Cited by 38
XIRL: Cross-embodiment inverse reinforcement learning
Zakka, K., Zeng, A., Florence, P., Tompson, J., Bohg, J., & Dwibedi, D. (2021) · arXiv · doi:10.48550/arxiv.2106.03911 · Cited by 38
Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents
Köster, R., Hadfield-Menell, D., Everett, R., Weidinger, L., Hadfield, G. K., & Leibo, J. Z. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2106028118 · Cited by 37
Safe Reinforcement Learning via Shielding
Alshiekh, M., Bloem, R., Ehlers, R., Könighofer, B., Niekum, S., & Topcu, U. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11797 · Cited by 37
PHYRE: A New Benchmark for Physical Reasoning
Bakhtin, A., van der Maaten, L., Johnson, J., Gustafson, L., & Girshick, R. (2019) · arXiv · doi:10.48550/arxiv.1908.05656 · Cited by 37
Learning offline: memory replay in biological and artificial reinforcement learning
Roscow, E. L., Chua, R., Costa, R. P., Jones, M. W., & Lepora, N. (2021) · Trends in Neurosciences · doi:10.1016/j.tins.2021.07.007 · Cited by 36
Yang, Y., Bevan, M. A., & Li, B. (2022) · Advanced Intelligent Systems · doi:10.1002/aisy.202200168 · Cited by 35
Algorithmic and Ethical Aspects of Recommender Systems in e-Commerce
Paraschakis, D. (2018) · doi:10.24834/2043/24268 · Cited by 35
Deep reinforcement learning and its applications in medical imaging and radiation therapy: a survey
Xu, L., Zhu, S., & Wen, N. (2022) · Physics in Medicine & Biology · doi:10.1088/1361-6560/ac9cb3 · Cited by 35
Reinforcement Learning with an Ensemble of Binary Action Deep Q-Networks
M. Hafiz, A., Hassaballah, M., Alqahtani, A., Alsubai, S., & Abdel Hameed, M. (2023) · Computer Systems Science and Engineering · doi:10.32604/csse.2023.031720 · Cited by 33
Optimal control of gene regulatory networks for morphogen-driven tissue patterning
Pezzotta, A., & Briscoe, J. (2023) · Cell Systems · doi:10.1016/j.cels.2023.10.004 · Cited by 34
Recognition of facial expression of fetuses by artificial intelligence (AI)
Miyagi, Y., Hata, T., Bouno, S., Koyanagi, A., & Miyake, T. (2021) · Journal of Perinatal Medicine · doi:10.1515/jpm-2020-0537 · Cited by 34
Predicting Game Difficulty and Churn Without Players
Roohi, S., Relas, A., Takatalo, J., Heiskanen, H., & Hämäläinen, P. (2020) · Proceedings of the Annual Symposium on Computer-Human Interaction in Play · doi:10.1145/3410404.3414235 · Cited by 34
“withtheresultconcatenatedwiththe other observations as shown in Figure 4. This is one of the default settings provided in Unity ML-agents, based on the architecture originally proposed by Mnih et al. [27]. 4.1.6 PPOandUnityMLparameters. The iteration experience budget of PPO agent is 10240 game moves. The agent collec…”
BackgroundInfluentialMARNet: Backdoor Attacks Against Cooperative Multi-Agent Reinforcement Learning
Chen, Y., Zheng, Z., & Gong, X. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2022.3207429 · Cited by 32
“A classical valued-based DRL algorithm is Deep Q-Learning [19] which extends the traditional Q-learning algorithm by using a neural network to represent the Q-value Qðs; aÞ.”
Deep Reinforcement Learning for Traffic Signal Control Model and Adaptation Study
Tan, J., Yuan, Q., Guo, W., Xie, N., Liu, F., Wei, J., & Zhang, X. (2022) · Sensors · doi:10.3390/s22228732 · Cited by 32
Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound
Yang, X., Dou, H., Huang, R., Xue, W., Huang, Y., Qian, J., Zhang, Y., Luo, H., Guo, H., Wang, T., et al. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3069663 · Cited by 32
Deep Reinforcement Active Learning for Medical Image Classification
Wang, J., Yan, Y., Zhang, Y., Cao, G., Yang, M., & Ng, M. K. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-59710-8_4 · Cited by 31
The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels
Stone, A., Ramirez, O., Konolige, K., & Jonschkowski, R. (2021) · arXiv · doi:10.48550/arxiv.2101.02722 · Cited by 31
“Learning successful policies from pixels in the Atari environment [9] was a major breakthrough in reinforcement learning that produced a surge of interest and advances in pixel-based RL.”
BackgroundSim-to-Real Transfer of Accurate Grasping with Eye-In-Hand Observations and Continuous Control
Yan, M., Frosio, I., Tyree, S., & Kautz, J. (2017) · arXiv · doi:10.48550/arxiv.1712.03303 · Cited by 31
“Deep RL algorithms have been successfully used to play Go and Atari games at superhuman level [11, 20, 21, 1].”
BackgroundMethodHow Does AI Improve Human Decision-Making? Evidence from the AI-Powered Go Program
Choi, S., Kim, N., Kim, J., & Kang, H. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3893835 · Cited by 30
Mankowitz, D., Mann, T., Bacon, P.-L., Precup, D., & Mannor, S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12115 · Cited by 30
Xu, Z., Wang, X., Wang, X., & Zheng, N. (2025) · Accident Analysis & Prevention · doi:10.1016/j.aap.2025.108011 · Cited by 29
EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading
Qin, M., Sun, S., Zhang, W., Xia, H., Wang, X., & An, B. (2023) · arXiv · doi:10.48550/arxiv.2309.12891 · Cited by 29
FinRL-podracer: high performance and scalable deep reinforcement learning for quantitative finance
Li, Z., Liu, X.-Y., Zheng, J., Wang, Z., Walid, A., & Guo, J. (2021) · Proceedings of the Second ACM International Conference on AI in Finance · doi:10.1145/3490354.3494413 · Cited by 28
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
Choshen, L., Fox, L., Aizenbud, Z., & Abend, O. (2019) · arXiv · doi:10.48550/arxiv.1907.01752 · Cited by 28
“…with the more common scenario studied by contemporary RL methods, which focuses mostly on much smaller discrete action spaces (e.g., video games (Mnih et al., 2015, 2016)), or continuous action spaces of relatively low dimensions (e.g., simulation of robotic con-trol tasks (Lillicrap et al.,…”
BackgroundLearning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation
Zhan, A., Zhao, R., Pinto, L., Abbeel, P., & Laskin, M. (2020) · arXiv · doi:10.48550/arxiv.2012.07975 · Cited by 28
Extendable and explainable deep learning for pan-cancer radiogenomics research
Liu, Q., & Hu, P. (2022) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2021.102111 · Cited by 27
Long, R., Sebo, J., Butlin, P., Finlinson, K., Fish, K., Harding, J., Pfau, J., Sims, T., Birch, J., & Chalmers, D. (2024) · arXiv · doi:10.48550/arxiv.2411.00986 · Cited by 27
Deep Active Inference for Partially Observable MDPs
van der Himst, O., & Lanillos, P. (2020) · arXiv · doi:10.48550/arxiv.2009.03622 · Cited by 27
Balaji, B., Mallya, S., Genc, S., Gupta, S., Dirac, L., Khare, V., Roy, G., Sun, T., Tao, Y., Townsend, B., et al. (2019) · arXiv · doi:10.48550/arxiv.1911.01562 · Cited by 27
“L G ] 5 N ov 2019 generalized to high dimensional problems with deep networks [40], [41], [42].”
BackgroundMethodDas, S. K., Mudi, R., Rahman, M. S., Rabie, K. M., & Li, X. (2024) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2024.3466858 · Cited by 27
“RL has proven its superiority and potential in wireless communication networks [174], but its deployment typically assumes a centralized system with global information, which may not be practical in reality [175] and may face feasibility challenges [176].”
BackgroundWilterson, A. I., & Graziano, M. S. A. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2102421118 · Cited by 26
“can earn are balanced for better learning (32).”
BackgroundInfluentialUncovering instabilities in variational-quantum deep Q-networks
Franz, M., Wolf, L., Periyasamy, M., Ufrecht, C., Scherer, D. D., Plinge, A., Mutschler, C., & Mauerer, W. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2022.08.021 · Cited by 26
“Although the results published in [32, 33] promise interesting properties, we show that VQ-DQN approaches are subject to instabilities that ultimately cause the learned policy to di-verge.”
BackgroundMethodInfluentialPattern recognition of human arm movement using deep reinforcement learning
Seok, W., Kim, Y., & Park, C. (2018) · 2018 International Conference on Information Networking (ICOIN) · doi:10.1109/icoin.2018.8343257 · Cited by 25
“MNIH, Volodymyr, et al introduced the experience replay [7].”
BackgroundOptimization of Neuroprosthetic Vision via End-to-end Deep Reinforcement Learning
Küçükoğlu, B., Rueckauer, B., Ahmad, N., de Ruyter van Steveninck, J., Güçlü, U., & van Gerven, M. (2022) · doi:10.1101/2022.02.25.482017 · Cited by 25
“Game difficulty in this context is defined by the performance of DQN [24] relative to human performance, which is 25%, 57%, and 1317% in Seaquest, Riverraid, and Breakout.”
BackgroundInfluentialOffline Meta-Reinforcement Learning with Online Self-Supervision
Pong, V. H., Nair, A., Smith, L., Huang, C., & Levine, S. (2021) · arXiv · doi:10.48550/arxiv.2107.03974 · Cited by 25
“where w̄ are target network weights [37] updated with the soft update [35] of w̄ ← η · w̄+ (1− η) ·w.”
Thinking While Moving: Deep Reinforcement Learning with Concurrent Control
Xiao, T., Jang, E., Kalashnikov, D., Levine, S., Ibarz, J., Hausman, K., & Herzog, A. (2020) · arXiv · doi:10.48550/arxiv.2004.06089 · Cited by 25
“In recent years, Deep Reinforcement Learning (DRL) methods have achieved tremendous success on a variety of diverse environments, including video games (Mnih et al., 2015), zero-sum games (Silver et al.”
BackgroundUrmonov, O., Aliev, H., & Kim, H. (2023) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3197880 · Cited by 24
“Using deep reinforcement learning (DRL), resource allocation in C-V2X network also can be effectively solved [10], [11].”
BackgroundHuman-like planning of swerve maneuvers for autonomous vehicles
Gu, T., Dolan, J. M., & Lee, J.-W. (2016) · 2016 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2016.7535466 · Cited by 24
Adaptive Information Seeking for Open-Domain Question Answering
Zhu, Y., Pang, L., Lan, Y., Shen, H., & Cheng, X. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.293 · Cited by 24
“Even though policies are usually trained via reinforcement learning, reinforcement learning algorithms (Sutton et al., 2000; Mnih et al., 2015) are often”
BackgroundGenerative Temporal Difference Learning for Infinite-Horizon Prediction
Janner, M., Mordatch, I., & Levine, S. (2020) · arXiv · doi:10.48550/arxiv.2010.14496 · Cited by 24
Hieu, N. Q., Anh, T. T., Luong, N. C., Niyato, D., Kim, D. I., & Elmroth, E. (2020) · arXiv · doi:10.48550/arxiv.2004.04104 · Cited by 23
“Thus, we propose to use the DQN [6], a combination of Q-learning and deep learning, to find the optimal policy for the MLMO.”
MethodKnow Your Mind: Adaptive Cognitive Activity Recognition with Reinforced CNN
Zhang, X., Yao, L., Wang, X., Zhang, W., Zhang, S., & Liu, Y. (2019) · 2019 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2019.00100 · Cited by 22
Metadata
- Authors
- Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Corresponding author
- Kavukcuoglu, Koray
- Hassabis, Demis
- ORCID
- Venue
- Nature
- Published
- 2015-02-25
- Volume
- 518
- Issue
- 7540
- Pages
- 529-533
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W2145339207
- Semantic Scholar
- 340f48901f72278f6bf78a04ee5b01df208cc508
- Cited by
- 30,357
- References
- 37
- Citations by year
- 2026: 2851 · 2025: 3619 · 2024: 3335 · 2023: 3592 · 2022: 3367 · 2021: 3971 · 2020: 3466 · 2019: 2907 · 2018: 1776 · 2017: 912 · 2016: 416 · 2015: 132
- FWCI
- 1057.57
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Nature (publishedVersion)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Funders
- DeepMind
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- deep Q-network, deep reinforcement learning, game-playing agents, end-to-end learning, deep neural network, temporal difference learning, dopaminergic neurons, human-level performance, DeepMind, AlphaGo, AlphaZero
- MeSH terms
- Algorithms, Artificial Intelligence, Humans, Models, Psychological, Reinforcement, Psychology, Reward, Neural Networks, Computer, Video Games
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.