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 501–600 of 1,418
Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K. O., & Clune, J. (2021) · Nature · doi:10.1038/s41586-020-03157-9 · Cited by 330
A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications
Mienye, I. D., & Swart, T. G. (2024) · Information · doi:10.3390/info15120755 · Cited by 330
Could a neuroscientist understand a microprocessor?
Jonas, E., & Paul Kording, K. (2016) · doi:10.1101/055624 · Cited by 329
“The simplicity of early video games has led to their use as model systems for reinforcement learning [14] and computational complexity research [15].”
BackgroundCyber security meets artificial intelligence: a survey
Li, J.-H. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1800573 · Cited by 329
Deep Reinforcement Learning in Parameterized Action SpacePreprint
Hausknecht, M., & Stone, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.04143 · Cited by 329
“A full list of state features may be found at https://github.com/mhauskn/ HFO/blob/master/doc/manual.pdf .”
BackgroundInfluentialReverse Curriculum Generation for Reinforcement Learning
Florensa, C., Held, D., Wulfmeier, M., Zhang, M., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05300 · Cited by 127
Robustness May Be at Odds with Accuracy
Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., & Mądry, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.12152 · Cited by 327
“Deep learning models have achieved impressive performance on a number of challenging benchmarks in computer vision, speech recognition and competitive game playing (Krizhevsky et al., 2012; Graves et al., 2013; Mnih et al., 2015; Silver et al., 2016; He et al., 2015a).”
BackgroundOboe: auto-tuning video ABR algorithms to network conditions
Akhtar, Z., Nam, Y. S., Govindan, R., Rao, S., Chen, J., Katz-Bassett, E., Ribeiro, B., Zhan, J., & Zhang, H. (2018) · Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication · doi:10.1145/3230543.3230558 · Cited by 327
Faust, A., Oslund, K., Ramirez, O., Francis, A., Tapia, L., Fiser, M., & Davidson, J. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461096 · Cited by 327
End-to-End Task-Completion Neural Dialogue SystemsPreprint
Li, X., Chen, Y.-N., Li, L. C., Gao, J., & Çelikyılmaz, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01008 · Cited by 327
Accessing Artificial Intelligence for Clinical Decision-Making
Giordano, C., Brennan, M., Mohamed, B., Rashidi, P., Modave, F., & Tighe, P. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.645232 · Cited by 326
“For example, deep reinforcement learning models (30, 31) are based on well-known concepts such as the Markov decision process (MDP) (32) and Q-learning (33) adapted to neural networks.”
MethodVirtual to Real Reinforcement Learning for Autonomous Driving
Pan, X., You, Y., Wang, Z., & Lu, C. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.11 · Cited by 326
“Recent work in deep reinforcement learning has made great progress in learning in a high dimensional space with the power of deep neural networks [13, 15, 17, 18, 24].”
BackgroundMethodQMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Rashid, T., Samvelyan, M., de Witt, C. S., Farquhar, G., Foerster, J., & Whiteson, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.11485 · Cited by 326
“Instead, the use of hyper-networks makes it possible to condition the weights of the monotonic network on s in an arbitrary way, thus integrating the full state s into the joint action-value estimates as QMIX is trained end-to-end to minimise the following loss: where b is the batch size of transitions sampled from th…”
MethodInfluentialEvaluation of Deep Learning Strategies for Nucleus Segmentation in Fluorescence Images
Caicedo, J. C., Roth, J., Goodman, A., Becker, T., Karhohs, K. W., Broisin, M., Molnar, C., McQuin, C., Singh, S., Theis, F. J., et al. (2019) · Cytometry Part A · doi:10.1002/cyto.a.23863 · Cited by 326
Application of deep learning to cybersecurity: A survey
Mahdavifar, S., & Ghorbani, A. A. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.02.056 · Cited by 325
Duan, J., Guan, Y., Li, S. E., Ren, Y., Sun, Q., & Cheng, B. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3082568 · Cited by 325
“Deep RL algorithms, such as deep Q-networks (DQNs) [1], employ a deep NN to estimate the Q value.”
BackgroundMethodInfluentialAljundi, R., Kelchtermans, K., & Tuytelaars, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01151 · Cited by 324
“For the latter, we take inspiration from the field of reinforcement learning, namely experience replay [22], although us-ing much smaller replay buffers, unlike very recent work of Rolnick et al. [31].”
BackgroundResultYan, C., Xiang, X., & Wang, C. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-01073-3 · Cited by 324
Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-Assisted Mobile Edge Computing
Wang, L., Wang, K., Pan, C., Xu, W., Aslam, N., & Nallanathan, A. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3059691 · Cited by 324
“Then, the DQN can be trained by minimizing the loss function [28].”
BackgroundMethodInfluentialLi, L., Wu, D., Huang, Y., & Yuan, Z.-M. (2021) · Applied Ocean Research · doi:10.1016/j.apor.2021.102759 · Cited by 323
Emergent Complexity via Multi-Agent Competition
Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., & Mordatch, I. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.03748 · Cited by 133
Deep reinforcement learning in recommender systems: A survey and new perspectives
Chen, X., Yao, L., McAuley, J., Zhou, G., & Wang, X. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110335 · Cited by 323
Interpretable End-to-End Urban Autonomous Driving With Latent Deep Reinforcement Learning
Chen, J., Li, S. E., & Tomizuka, M. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3046646 · Cited by 322
Review of Autonomous Path Planning Algorithms for Mobile Robots
Qin, H., Shao, S., Wang, T., Yu, X., Jiang, Y., & Cao, Z. (2023) · Drones · doi:10.3390/drones7030211 · Cited by 322
A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem
Jiang, Z., Xu, D., & Liang, J. (2017) · arXiv · doi:10.48550/arxiv.1706.10059 · Cited by 321
Ielmini, D., & Ambrogio, S. (2020) · Nanotechnology · doi:10.1088/1361-6528/ab554b · Cited by 321
Qie, H., Shi, D., Shen, T., Xu, X., Li, Y., & Wang, L. (2019) · IEEE Access · doi:10.1109/access.2019.2943253 · Cited by 321
Wei, Y., Yu, F. R., Song, M., & Han, Z. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2878435 · Cited by 321
Teacher–Student Curriculum Learning
Matiisen, T., Oliver, A., Cohen, T., & Schulman, J. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2934906 · Cited by 320
Artificial Intelligence for Vehicle-to-Everything: A Survey
Tong, W., Hussain, A., Bo, W. X., & Maharjan, S. (2019) · IEEE Access · doi:10.1109/access.2019.2891073 · Cited by 320
Multimodal end-to-end autonomous driving
Xiao, Y., Codevilla, F., Gurram, A., Urfalioglu, O., & Lopez, A. M. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3013234 · Cited by 319
Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks
Yu, Y., Wang, T., & Liew, S. C. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904329 · Cited by 319
Deep-Reinforcement-Learning-Based Offloading Scheduling for Vehicular Edge Computing
Zhan, W., Luo, C., Wang, J., Wang, C., Min, G., Duan, H., & Zhu, Q. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2978830 · Cited by 319
“Value-based DRL methods adopt DNNs to approximate the value function (called value network), e.g., deep Q-network (DQN) [23] and double DQN [24].”
MethodExplainability in deep reinforcement learning
Heuillet, A., Couthouis, F., & Díaz-Rodríguez, N. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106685 · Cited by 319
Khalil, R. A., Saeed, N., Masood, M., Fard, Y. M., Alouini, M.-S., & Al-Naffouri, T. Y. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3051414 · Cited by 318
Huang, S., Yang, J., Shen, N., Xu, Q., & Zhao, Q. (2023) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2023.01.006 · Cited by 317
An Introduction to Neural Information Retrieval
Mitra, B., & Craswell, N. (2018) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000061 · Cited by 317
Machine learning applications in minerals processing: A review
McCoy, J. T., & Auret, L. (2019) · Minerals Engineering · doi:10.1016/j.mineng.2018.12.004 · Cited by 317
Hao, X., Zhang, G., & Ma, S. (2016) · International Journal of Semantic Computing · doi:10.1142/s1793351x16500045 · Cited by 317
Singla, A., Padakandla, S., & Bhatnagar, S. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2954952 · Cited by 317
Deep learning in ultrasound imaging
van Sloun, R. J. G., Cohen, R., & Eldar, Y. C. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2932116 · Cited by 316
Personalized machine learning for robot perception of affect and engagement in autism therapy
Rudovic, O., Lee, J., Dai, M., Schuller, B., & Picard, R. W. (2018) · Science Robotics · doi:10.1126/scirobotics.aao6760 · Cited by 316
Wu, L., Zhang, J., Zhou, W., An, P., Shen, L., Liu, J., Jiang, X., Huang, X., Mu, G., Wan, X., et al. (2019) · Gut · doi:10.1136/gutjnl-2018-317366 · Cited by 316
Machine learning for active matter
Cichos, F., Gustavsson, K., Mehlig, B., & Volpe, G. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0146-9 · Cited by 315
Drone Deep Reinforcement Learning: A Review
Azar, A. T., Koubaa, A., Ali Mohamed, N., Ibrahim, H. A., Ibrahim, Z. F., Kazim, M., Ammar, A., Benjdira, B., Khamis, A. M., Hameed, I. A., et al. (2021) · Electronics · doi:10.3390/electronics10090999 · Cited by 314
“Another proposed idea was to use experience replay, which a biologically inspired mechanism [55], and it is based on randomizing the data and removing the correlation in the different states.”
MethodApplication of machine learning in intelligent fish aquaculture: A review
Zhao, S., Zhang, S., Liu, J., Wang, H., Zhu, J., Li, D., & Zhao, R. (2021) · Aquaculture · doi:10.1016/j.aquaculture.2021.736724 · Cited by 314
Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
Zhang, Z., Geiger, J., Pohjalainen, J., Mousa, A. E.-D., Jin, W., & Schuller, B. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3178115 · Cited by 313
Enhancing transportation systems via deep learning: A survey
Wang, Y., Zhang, D., Liu, Y., Dai, B., & Lee, L. H. (2019) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2018.12.004 · Cited by 312
Deep Reinforcement Learning for Internet of Things: A Comprehensive Survey
Chen, W., Qiu, X., Cai, T., Dai, H.-N., Zheng, Z., & Zhang, Y. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3073036 · Cited by 311
MOReL : Model-Based Offline Reinforcement Learning
Kidambi, R., Rajeswaran, A., Netrapalli, P., & Joachims, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.05951 · Cited by 152
Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans
Ghesu, F.-C., Georgescu, B., Zheng, Y., Grbic, S., Maier, A., Hornegger, J., & Comaniciu, D. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2782687 · Cited by 310
“9 Optimization method RMS-prop [19] Learning rate 0.”
InfluentialD4RL: Datasets for Deep Data-Driven Reinforcement Learning
Fu, J., Kumar, A., Nachum, O., Tucker, G., & Levine, S. (2020) · arXiv · doi:10.48550/arxiv.2004.07219 · Cited by 310
Reinforcement Learning in Different Phases of Quantum Control
Bukov, M., Day, A. G. R., Sels, D., Weinberg, P., Polkovnikov, A., & Mehta, P. (2018) · Physical Review X · doi:10.1103/physrevx.8.031086 · Cited by 310
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
Li, S., Xue, M., Zhao, B., Zhu, H., & Zhang, X. (2020) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2020.3021407 · Cited by 310
Deep reinforcement learning for dynamic scheduling of a flexible job shop
Liu, R., Piplani, R., & Toro, C. (2022) · International Journal of Production Research · doi:10.1080/00207543.2022.2058432 · Cited by 310
Li, G., Yang, Y., Li, S., Qu, X., Lyu, N., & Li, S. E. (2022) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2021.103452 · Cited by 308
Approximated and User Steerable tSNE for Progressive Visual Analytics
Pezzotti, N., Lelieveldt, B. P. F., Maaten, L. V. D., Hollt, T., Eisemann, E., & Vilanova, A. (2017) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2016.2570755 · Cited by 308
Faes, L., Wagner, S. K., Fu, D. J., Liu, X., Korot, E., Ledsam, J. R., Back, T., Chopra, R., Pontikos, N., Kern, C., et al. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30108-6 · Cited by 308
Hoel, C.-J., Driggs-Campbell, K., Wolff, K., Laine, L., & Kochenderfer, M. J. (2020) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2019.2955905 · Cited by 308
Neural circuit policies enabling auditable autonomy
Lechner, M., Hasani, R., Amini, A., Henzinger, T. A., Rus, D., & Grosu, R. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00237-3 · Cited by 308
“Although deep learning algorithms have achieved noteworthy successes in various high-dimensional tasks 2,12–16 , there still are important representation-learning challenges 17–19 that have to be addressed.”
BackgroundCertifying Some Distributional Robustness with Principled Adversarial Training
Sinha, A., Namkoong, H., Volpi, R., & Duchi, J. C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10571 · Cited by 307
“In scenarios where the underlying environment has a continuous state-space and we represent Q with a differentiable function (e.g. [ 33]), we can modify the update (19) with an adversarial state perturbation to incorporate distributional robustness.”
Multi-Agent Deep Reinforcement Learning for Urban Traffic Light Control in Vehicular Networks
Wu, T., Zhou, P., Liu, K., Yuan, Y., Wang, X., Huang, H., & Wu, D. O. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2997896 · Cited by 307
“The combination of the fast-developing deep learning and traditional reinforcement learning further solve this problem, i.e., Deep Reinforcement Learning (DRL) [17], [18].”
BackgroundFrom Machine Learning to Explainable AI
Holzinger, A. (2018) · 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA) · doi:10.1109/disa.2018.8490530 · Cited by 306
Deep reinforcement learning for energy management in a microgrid with flexible demand
Nakabi, T. A., & Toivanen, P. (2021) · Sustainable Energy, Grids and Networks · doi:10.1016/j.segan.2020.100413 · Cited by 306
A review of reinforcement learning for autonomous building energy management
Mason, K., & Grijalva, S. (2019) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2019.07.019 · Cited by 306
A survey on computation offloading modeling for edge computing
Lin, H., Zeadally, S., Chen, Z., Labiod, H., & Wang, L. (2020) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2020.102781 · Cited by 305
Continuous Deep Q-Learning with Model-based Acceleration
Gu, S., Lillicrap, T., Sutskever, I., & Levine, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.00748 · Cited by 304
A deep feature based framework for breast masses classification
Jiao, Z., Gao, X., Wang, Y., & Li, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.02.060 · Cited by 304
A survey of multi-agent deep reinforcement learning with communication
Zhu, C., Dastani, M. M., & Wang, S. (2024) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-023-09633-6 · Cited by 391
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
Al-Shedivat, M., Bansal, T., Burda, Y., Sutskever, I., Mordatch, I., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.03641 · Cited by 140
“At each iteration k we (a) randomly select an opponent from the training pool, (b) sample a version of the opponent’s policy to be in [1 , k ] (this ensures that even when the opponent is strong, sometimes an undertrained version is selected which allows the agent learn to win at early stages), and…”
BackgroundMethodLearning Heuristics for the TSP by Policy Gradient
Deudon, M., Cournut, P., Lacoste, A., Adulyasak, Y., & Rousseau, L.-M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93031-2_12 · Cited by 303
Machine learning for vehicular networks: Recent advances and application examples
Ye, H., Liang, L., Ye Li, G., Kim, J., Lu, L., & Wu, M. (2018) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2018.2811185 · Cited by 303
DyNet: The Dynamic Neural Network Toolkit
Neubig, G., Dyer, C., Goldberg, Y., Matthews, A., Ammar, W., Anastasopoulos, A., Ballesteros, M., Chiang, D., Clothiaux, D., Cohn, T., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.03980 · Cited by 302
“Deep neural networks are now an indispensable tool in the machine learning practitioner’s toolbox, powering applications from image understanding [39], speech recognition and synthesis [29, 65], game playing [45, 54], language modeling and analysis [6, 14], and more.”
MethodResource Allocation Based on Deep Reinforcement Learning in IoT Edge Computing
Xiong, X., Zheng, K., Lei, L., & Hou, L. (2020) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.2986615 · Cited by 302
Artificial Intelligence Empowered Edge Computing and Caching for Internet of Vehicles
Dai, Y., Xu, D., Maharjan, S., Qiao, G., & Zhang, Y. (2019) · IEEE Wireless Communications · doi:10.1109/mwc.2019.1800411 · Cited by 302
“DQN: DQN is a kind of deep reinforcement learning algorithm that uses deep neural networks instead of Q-function to explore actions [14].”
BackgroundOh, C., Song, J., Choi, J., Kim, S., Lee, S., & Suh, B. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174223 · Cited by 301
State representation learning for control: An overview
Lesort, T., Díaz-Rodríguez, N., Goudou, J.-F., & Filliat, D. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.006 · Cited by 301
Secure and Efficient Federated Learning for Smart Grid With Edge-Cloud Collaboration
Su, Z., Wang, Y., Luan, T. H., Zhang, N., Li, F., Chen, T., & Cao, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3095506 · Cited by 301
Liu, C. H., Ma, X., Gao, X., & Tang, J. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2908171 · Cited by 301
Catalyzing next-generation Artificial Intelligence through NeuroAI
Zador, A., Escola, S., Richards, B., Ölveczky, B., Bengio, Y., Boahen, K., Botvinick, M., Chklovskii, D., Churchland, A., Clopath, C., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-37180-x · Cited by 300
“Modern AI can easily learn to outperform humans at video games like Breakout using nothing more than pixels on a screen and game scores 34 .”
BackgroundRecurrent Experience Replay in Distributed Reinforcement Learning.
Kapturowski, S., Ostrovski, G., Quan, J., Munos, R., & Dabney, W. (2018) · International Conference on Learning Representations · Cited by 635
Self-citationReinforcement Learning with Augmented Data
Laskin, M., Lee, K., Stooke, A., Pinto, L., Abbeel, P., & Srinivas, A. (2020) · arXiv · doi:10.48550/arxiv.2004.14990 · Cited by 299
Liu, N., Li, Z., Xu, J., Xu, Z., Lin, S., Qiu, Q., Tang, J., & Wang, Y. (2017) · 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.123 · Cited by 299
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Tessler, C., Givony, S., Zahavy, T., Mankowitz, D., & Mannor, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10744 · Cited by 299
Zhou, M., Yu, Y., & Qu, X. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2942014 · Cited by 299
(2017) · doi:10.1109/intellisys.2017.8324237 · Cited by 298
Cryptocurrency Portfolio Management with Deep Reinforcement Learning
Jiang, Z., & Liang, J. (2016) · arXiv · doi:10.48550/arxiv.1612.01277 · Cited by 298
On Tiny Episodic Memories in Continual Learning
Chaudhry, A., Rohrbach, M., Elhoseiny, M., Ajanthan, T., Dokania, P. K., Torr, P. H. S., & Ranzato, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.10486 · Cited by 298
Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges
Lei, L., Tan, Y., Zheng, K., Liu, S., Zhang, K., & Shen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2988367 · Cited by 298
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
Marcus, G. (2020) · arXiv · doi:10.48550/arxiv.2002.06177 · Cited by 297
“ould decipher complex sentences like does the shortest thing the tallest pyramid's support supports support anything green? THE NEXT DECADE IN AI / GARY MARCUS 7 much-heralded Atari game system (Mnih et al., 2015) which, as discussed later, succeeded in playing a wide variety of games without any use detailed cog…”
Background#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Tang, H., Houthooft, R., Foote, D., Stooke, A., Chen, X., Duan, Y., Schulman, J., Turck, F. D., & Abbeel, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04717 · Cited by 296
“In contrast, contemporary deep RL algorithms propagate the bonus signal based on rollouts collected from interacting with environments, with value-based (Mnih et al., 2015) or policy gradient-based (Schulman et al., 2015; Mnih et al., 2016) methods, at limited speed.”
InfluentialModel-free Deep Reinforcement Learning for Urban Autonomous Driving
Chen, J., Yuan, B., & Tomizuka, M. (2019) · 2019 IEEE Intelligent Transportation Systems Conference (ITSC) · doi:10.1109/itsc.2019.8917306 · Cited by 296
“Related algorithms range from the Q learning based approaches such as DQN [19], [20] and double DQN [29], the actor-critic approaches such as A3C [18], DDPG [17] and TD3 [11], the policy optimization approaches such as TRPO [23] and PPO [24], and the maximum entropy approaches such as soft actor-critic [13], [14].”
BackgroundMethodActive learning machine learns to create new quantum experiments
Melnikov, A. A., Poulsen Nautrup, H., Krenn, M., Dunjko, V., Tiersch, M., Zeilinger, A., & Briegel, H. J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1714936115 · Cited by 296
Seismic Waveform Classification and First-Break Picking Using Convolution Neural Networks
Yuan, S., Liu, J., Wang, S., Wang, T., & Shi, P. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2785834 · Cited by 296
Deep learning for hybrid 5G services in mobile edge computing systems: learn from a digital twin
Dong, R., She, C., Hardjawana, W., Li, Y., & Vucetic, B. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2927312 · Cited by 295
Toward Autonomous Multi-UAV Wireless Network: A Survey of Reinforcement Learning-Based Approaches
Bai, Y., Zhao, H., Zhang, X., Chang, Z., Jäntti, R., & Yang, K. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3323344 · Cited by 295
“This enables the RL algorithms can handle high-dimensional state and action spaces [12].”
Review on deep learning applications in frequency analysis and control of modern power system
Zhang, Y., Shi, X., Zhang, H., Cao, Y., & Terzija, V. (2022) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.107744 · Cited by 295
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
Zhang, K., Yang, Z., Liu, H., Zhang, T., & Başar, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08757 · Cited by 293
“For example, Gruslys et al. (2017); Wang et al. (2016); Gu et al. (2017) have proposed sample-e ffi cient actor-critic algorithms based on experience replay (Mnih et al., 2015) and o ff -policy learning (Munos et al., 2016).”
MethodDeep Reinforcement Learning for Strategic Bidding in Electricity Markets
Ye, Y., Qiu, D., Sun, M., Papadaskalopoulos, D., & Strbac, G. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2019.2936142 · Cited by 293
Guo, C., Wang, X., Zheng, Y., & Zhang, F. (2022) · Energy · doi:10.1016/j.energy.2021.121873 · Cited by 293
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.