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 801–900 of 1,418
Deep Learning Approximation for Stochastic Control ProblemsPreprint
Han, J., & Weinan, E. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.07422 · Cited by 283
Challenges of Real-World Reinforcement Learning
Dulac-Arnold, G., Mankowitz, D. J., & Hester, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12901 · Cited by 238
Automated Search for new Quantum Experiments
Krenn, M., Malik, M., Fickler, R., Lapkiewicz, R., & Zeilinger, A. (2016) · Physical Review Letters · doi:10.1103/physrevlett.116.090405 · Cited by 238
Preparing for the unknown: Learning a universal policy with online system identification
Yu, W., Tan, J., Karen Liu, C., & Turk, G. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.048 · Cited by 237
Preparing for the Unknown: Learning a Universal Policy with Online System Identification
Yu, W., Tan, J., Liu, C. K., & Turk, G. (2017) · arXiv · doi:10.48550/arxiv.1702.02453 · Cited by 237
“Lillicrap et al. [18] extended their work of Deep Q-Learning [19] and Deterministic Policy Gradient (DPG) [31] to learn robotic motor skills such as hopping, reaching and 2D walking directly from pixel input.”
BackgroundA Distributional Perspective on Reinforcement Learning
Bellemare, M. G., Dabney, W., & Munos, R. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.06887 · Cited by 237
“Although DQN is mostly robust to stochastic execution, there are a few games in which its performance is reduced.”
MethodInfluentialSelf-citationReward Constrained Policy Optimization
Tessler, C., Mankowitz, D. J., & Mannor, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.11074 · Cited by 237
“This poses an issue, as Q-learning algorithms such as DQN (Mnih et al., 2015) do not learn a parametrization of the policy, and common Actor-Critic methods (e.g. (Schulman et al., 2015a; Mnih et al., 2016; et al., 2017)) build the reward-to-go based on an N-step sample and a bootstrap update from…”
MethodInfluentialA Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments
Padakandla, S. (2022) · ACM Computing Surveys · doi:10.1145/3459991 · Cited by 237
A Survey of Deep RL and IL for Autonomous Driving Policy Learning
Zhu, Z., & Zhao, H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3134702 · Cited by 237
Efficient Ridesharing Order Dispatching with Mean Field Multi-Agent Reinforcement Learning
Li, M., Qin, Z., Jiao, Y., Yang, Y., Wang, J., Wang, C., Wu, G., & Ye, J. (2019) · The World Wide Web Conference · doi:10.1145/3308558.3313433 · Cited by 237
“ther than a given agent i with the subscript −i, e.g., a ≡(at −i ,a t i ). To stabilize the training process, we maintain an experience replay bufferDcontaining tuples (ot ,at rt,ot+1)as described in [26]. 2.1.2 Dynamic of the Action Set Elements. In the order dispatching problem, an action is defined as an active ord…”
MethodInfluentialEvent-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines
Neftci, E. O., Augustine, C., Paul, S., & Detorakis, G. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00324 · Cited by 237
Biological underpinnings for lifelong learning machines
Kudithipudi, D., Aguilar-Simon, M., Babb, J., Bazhenov, M., Blackiston, D., Bongard, J., Brna, A. P., Chakravarthi Raja, S., Cheney, N., Clune, J., et al. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00452-0 · Cited by 236
“…attention 69–71 , noradrenaline (NA) drives responses to novelty and surprise, serotonin (5-HT) can shift patience and assertiveness depending on the context 72 and dopamine carries a reward prediction error signal 73 , which has been an inspiration for reinforcement learning algorithms 74,75 .”
BackgroundA predictive safety filter for learning-based control of constrained nonlinear dynamical systems
Wabersich, K. P., & Zeilinger, M. N. (2021) · Automatica · doi:10.1016/j.automatica.2021.109597 · Cited by 236
Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks
Behzadan, V., & Munir, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-62416-7_19 · Cited by 236
A review of artificial intelligence applied to path planning in UAV swarms
Puente-Castro, A., Rivero, D., Pazos, A., & Fernandez-Blanco, E. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06569-4 · Cited by 236
“This type of algorithm is known as Deep Q-Learning and is part of the well-known Deep RL [68].”
MethodComparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
Lin, Y., McPhee, J., & Azad, N. L. (2021) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2020.3012947 · Cited by 236
“They include target networks, mini-batch gradient descent, experience replay, batch normalization, and addition of Gaussian noise to the action for exploration [3], [40], [41].”
BackgroundMethodRandomized Prior Functions for Deep Reinforcement Learning
Osband, I., Aslanides, J., & Cassirer, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03335 · Cited by 103
The Hanabi challenge: A new frontier for AI research
Bard, N., Foerster, J. N., Chandar, S., Burch, N., Lanctot, M., Song, H. F., Parisotto, E., Dumoulin, V., Moitra, S., Hughes, E., et al. (2020) · Artificial Intelligence · doi:10.1016/j.artint.2019.103216 · Cited by 235
“inbow-Agent. Rainbow [33] is a state of the art agent architecture for deep RL on the Arcade Learning Environment. It combines some of the key innovations that have been made to Deep Q-Networks (DQN) [34] over the last few years, resulting in a learning algorithm that is both sample ecient and achieves high rewards at…”
MethodSelf-citationPhotonic multiplexing techniques for neuromorphic computing
Bai, Y., Xu, X., Tan, M., Sun, Y., Li, Y., Wu, J., Morandotti, R., Mitchell, A., Xu, K., & Moss, D. J. (2023) · Nanophotonics · doi:10.1515/nanoph-2022-0485 · Cited by 235
Reaching the limit in autonomous racing: Optimal control versus reinforcement learning
Song, Y., Romero, A., Müller, M., Koltun, V., & Scaramuzza, D. (2023) · Science Robotics · doi:10.1126/scirobotics.adg1462 · Cited by 235
Deep reinforcement learning for inventory control: A roadmap
Boute, R. N., Gijsbrechts, J., van Jaarsveld, W., & Vanvuchelen, N. (2022) · European Journal of Operational Research · doi:10.1016/j.ejor.2021.07.016 · Cited by 235
Di, X., & Shi, R. (2021) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2021.103008 · Cited by 235
Deep reinforcement learning for automated radiation adaptation in lung cancer
Tseng, H., Luo, Y., Cui, S., Chien, J., Ten Haken, R. K., & Naqa, I. E. (2017) · Medical Physics · doi:10.1002/mp.12625 · Cited by 235
Luo, S., Zhang, L., & Fan, Y. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3104716 · Cited by 235
Learning Policies for Adaptive Tracking with Deep Feature Cascades
Huang, C., Lucey, S., & Ramanan, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.21 · Cited by 235
“Note such a reward scheme implicitly penalizes a large number of layers l since Q-learning (detailed next) models the expected future rewards when deciding on an action (positive or negative).”
BackgroundMethodInfluentialReinforcement learning in sustainable energy and electric systems: a survey
Yang, T., Zhao, L., Li, W., & Zomaya, A. Y. (2020) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2020.03.001 · Cited by 234
Cooperative Deep Reinforcement Learning for Large-Scale Traffic Grid Signal Control
Tan, T., Bao, F., Deng, Y., Jin, A., Dai, Q., & Wang, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2904742 · Cited by 234
Deep reinforcement learning enabled self-learning control for energy efficient driving
Qi, X., Luo, Y., Wu, G., Boriboonsomsin, K., & Barth, M. (2019) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2018.12.018 · Cited by 234
Xu, X., Shen, B., Ding, S., Srivastava, G., Bilal, M., Khosravi, M. R., Menon, V. G., Jan, M. A., & Wang, M. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3040180 · Cited by 234
Wang, Y., Fang, W., Ding, Y., & Xiong, N. (2021) · Wireless Networks · doi:10.1007/s11276-021-02632-z · Cited by 234
“By combining deep neural networks (DNNs) with Q-learning, DQN [23] addresses the short-comings of Q-learning.”
MethodReinforcement Learning with Neural Networks for Quantum Feedback
Fösel, T., Tighineanu, P., Weiss, T., & Marquardt, F. (2018) · Max Planck Digital Library · Cited by 238
Recent advances of deep learning in bioinformatics and computational biology
Tang, B., Pan, Z., Yin, K., & Khateeb, A. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00214 · Cited by 233
FeUdal Networks for Hierarchical Reinforcement Learning
Vezhnevets, A., Osindero, S., Schaul, T., Heess, N., Jaderberg, M., Silver, D., & Kavukcuoglu, K. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01161 · Cited by 233
Self-citationCollision Avoidance in Pedestrian-Rich Environments With Deep Reinforcement Learning
Everett, M., Chen, Y. F., & How, J. P. (2021) · IEEE Access · doi:10.1109/access.2021.3050338 · Cited by 233
“a deep neural network (DNN) parameterized by weights and biases, θ , as in [23].”
MethodSQIL: Imitation Learning via Reinforcement Learning with Sparse RewardsPreprint
Reddy, S., Dragan, A. D., & Levine, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11108 · Cited by 303
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
Eslami, S. M. A., Heess, N., Weber, T., Tassa, Y., Szepesvári, D., Kavukcuoglu, K., & Hinton, G. E. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.08575 · Cited by 232
Self-citationThakkar, A., & Chaudhari, K. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114800 · Cited by 232
Tian, Y., Li, X., Ma, H., Zhang, X., Tan, K. C., & Jin, Y. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3146882 · Cited by 232
Reinforcement Learning with Neural Networks for Quantum Feedback
Fösel, T., Tighineanu, P., Weiss, T., & Marquardt, F. (2018) · Physical Review X · doi:10.1103/physrevx.8.031084 · Cited by 231
Tufail, S., Riggs, H., Tariq, M., & Sarwat, A. I. (2023) · Electronics · doi:10.3390/electronics12081789 · Cited by 231
Ozawa, T., Ishihara, S., Fujishiro, M., Saito, H., Kumagai, Y., Shichijo, S., Aoyama, K., & Tada, T. (2019) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2018.10.020 · Cited by 231
Learning to Act by Predicting the Future
Dosovitskiy, A., & Koltun, V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01779 · Cited by 56
Gao, J., Shen, Y., Liu, J., Ito, M., & Shiratori, N. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.02755 · Cited by 231
“The explanation for why experience replay and target network mechanisms can improve algorithm stability has been given in [11].”
BackgroundMethodInfluentialDeep Reinforcement Learning for Sequence-to-Sequence Models
Keneshloo, Y., Shi, T., Ramakrishnan, N., & Reddy, C. K. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2929141 · Cited by 230
Improving Robot Controller Transparency Through Autonomous Policy Explanation
Hayes, B., & Shah, J. A. (2017) · Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction · doi:10.1145/2909824.3020233 · Cited by 230
“We demonstrate our approach’s utility within three representative domains (discrete, continuous, and multi-agent) that map to three important classes of robot controllers, including hard-coded, conditional statement-driven policies, and those that rely upon trained reinforcement learning models [18] — demonstrating su…”
BackgroundScope of machine learning in materials research—A review
Mobarak, M. H., Mimona, M. A., Islam, M. A., Hossain, N., Zohura, F. T., Imtiaz, I., & Rimon, M. I. H. (2023) · Applied Surface Science Advances · doi:10.1016/j.apsadv.2023.100523 · Cited by 230
Understanding RealWorld Indoor Scenes with Synthetic Data
Handa, A., Patraucean, V., Badrinarayanan, V., Stent, S., & Cipolla, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.442 · Cited by 230
Using a Deep Reinforcement Learning Agent for Traffic Signal Control
Genders, W., & Razavi, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01142 · Cited by 229
Migration Modeling and Learning Algorithms for Containers in Fog Computing
Tang, Z., Zhou, X., Zhang, F., Jia, W., & Zhao, W. (2019) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2018.2827070 · Cited by 229
Interactive Path Reasoning on Graph for Conversational Recommendation
Lei, W., Zhang, G., He, X., Miao, Y., Wang, X., Chen, L., & Chua, T.-S. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403258 · Cited by 228
“It is also noticeable that, since our policy network have much smaller actions space and we adopt Deep Q-learning, the network is easier to converge.”
MethodInfluentialLearning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
Zhang, C., Song, W. W., Cao, Z., Zhang, J., Tan, P. S., & Xu, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12367 · Cited by 228
Crandall, J. W., Oudah, M., Tennom, Ishowo-Oloko, F., Abdallah, S., Bonnefon, J.-F., Cebrian, M., Shariff, A., Goodrich, M. A., & Rahwan, I. (2018) · Nature Communications · doi:10.1038/s41467-017-02597-8 · Cited by 228
FACMAC: Factored Multi-Agent Centralised Policy GradientsPreprint
Peng, B., Rashid, T., de Witt, C. A. S., Kamienny, P.-A., Torr, P. H. S., Böhmer, W., & Whiteson, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.06709 · Cited by 270
“Here r is the global reward, and φ− and ψ− are parameters of the target Q and mixing network, respectively, as in DQN [24].”
BackgroundLin, Z., Ni, Z., Kuang, L., Jiang, C., & Huang, Z. W. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3145848 · Cited by 249
Multi-DQN: An ensemble of Deep Q-learning agents for stock market forecasting
Carta, S., Ferreira, A., Podda, A. S., Reforgiato Recupero, D., & Sanna, A. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113820 · Cited by 226
“We choose the Deep Q-learning algorithm in RL, initially presented by Mnih et al. (2015), applied to intraday stock market trading.”
MethodMulti-UAV Path Planning for Wireless Data Harvesting With Deep Reinforcement Learning
Bayerlein, H., Theile, M., Caccamo, M., & Gesbert, D. (2021) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2021.3081996 · Cited by 226
Robust non-rigid registration through agent-based action learning
Krebs, J., Mansi, T., Delingette, H., Zhang, L., Ghesu, F. C., Miao, S., Maier, A. K., Ayache, N., Liao, R., & Kamen, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-66182-7_40 · Cited by 225
A Study on Overfitting in Deep Reinforcement Learning
Zhang, C., Vinyals, O., Munos, R., & Bengio, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.06893 · Cited by 225
Cognitive Mapping and Planning for Visual Navigation
Gupta, S., Tolani, V., Davidson, J., Levine, S., Sukthankar, R., & Malik, J. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01236-7 · Cited by 225
BayesFlow: Learning Complex Stochastic Models With Invertible Neural Networks
Radev, S. T., Mertens, U. K., Voss, A., Ardizzone, L., & Kothe, U. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3042395 · Cited by 225
Tang, H., Rabault, J., Kuhnle, A., Wang, Y., & Wang, T. (2020) · Physics of Fluids · doi:10.1063/5.0006492 · Cited by 225
Learning Navigation Behaviors End-to-End With AutoRL
Chiang, H.-T. L., Faust, A., Fiser, M., & Francis, A. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2899918 · Cited by 225
Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios
Li, G., Yang, Y., Zhang, T., Qu, X., Cao, D., Cheng, B., & Li, K. (2021) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102820 · Cited by 225
Recent progress in analog memory-based accelerators for deep learning
Tsai, H., Ambrogio, S., Narayanan, P., Shelby, R. M., & Burr, G. W. (2018) · Journal of Physics D: Applied Physics · doi:10.1088/1361-6463/aac8a5 · Cited by 225
Human-robot collaboration in disassembly for sustainable manufacturing
Liu, Q., Liu, Z., Xu, W., Tang, Q., Zhou, Z., & Pham, D. T. (2019) · International Journal of Production Research · doi:10.1080/00207543.2019.1578906 · Cited by 224
Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Narvekar, S., Peng, B., Leonetti, M., Sinapov, J., Taylor, M. E., & Stone, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04960 · Cited by 224
“At each training step, experience tuples are sampled from the buffer and used to train DQN in minibatches.”
BackgroundInfluential(2021) · Journal of Machine Learning Research · Cited by 224
A critical review of state‐of‐the‐art chatbot designs and applications
Luo, B., Lau, R. Y. K., Li, C., & Si, Y. (2022) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1434 · Cited by 224
Reinforcement learning for batch bioprocess optimization
Petsagkourakis, P., Sandoval, I. O., Bradford, E., Zhang, D., & del Rio-Chanona, E. A. (2020) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2019.106649 · Cited by 224
An application of deep reinforcement learning to algorithmic trading
Théate, T., & Ernst, D. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114632 · Cited by 224
“lected at any point during training. For the sake of brevity, the DQN algorithm is illustrated in Figure 3, but is not extensively presented in this paper. Besides the original publications ([20] and [22]), there exists a great scientic literature around this algorithm, see for instance [23], [24], [25], [26], [27] an…”
MethodSupervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation
Wang, L., Zhang, W., He, X., & Zha, H. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219961 · Cited by 223
“deterministic policy, the Q value can be calculated with dynamic programming as follows: Qµ(st,at)= Er t,s t+1∼E[r(st,at)+γQ µ(st+1,µt+1)], (1) where E indicates the environment. Deep Q network (DQN) [23] utilizes deep learning to estimate a non-linear Q function Qw(s,a) parameterized by w. The strategy of replay buff…”
MethodShafiq, M., Tian, Z., Bashir, A. K., Jolfaei, A., & Yu, X. (2020) · Sustainable Cities and Society · doi:10.1016/j.scs.2020.102177 · Cited by 223
Deep Reinforcement Learning for Resource Allocation in V2V Communications
Ye, H., & Li, G. Y. (2018) · 2018 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2018.8422586 · Cited by 222
Proximal Policy Optimization With Policy Feedback
Gu, Y., Cheng, Y., Chen, C. L. P., & Wang, X. (2022) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2021.3098451 · Cited by 222
“Value-based DRL algorithms originate from the classic deep Q network (DQN) [8].”
BackgroundManaging engineering systems with large state and action spaces through deep reinforcement learning
Andriotis, C. P., & Papakonstantinou, K. G. (2019) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2019.04.036 · Cited by 222
Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
Wang, M., & Deng, W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00934 · Cited by 222
Recent Advances in Transparent Electronics with Stretchable Forms
Kim, K., Park, Y., Hyun, B. G., Choi, M., & Park, J. (2019) · Advanced Materials · doi:10.1002/adma.201804690 · Cited by 222
Yang, T., Zhao, L., Li, W., & Zomaya, A. Y. (2021) · Energy · doi:10.1016/j.energy.2021.121377 · Cited by 222
Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
Rusek, K., Suárez-Varela, J., Mestres, A., Barlet-Ros, P., & Cabellos-Aparicio, A. (2019) · Proceedings of the 2019 ACM Symposium on SDN Research · doi:10.1145/3314148.3314357 · Cited by 221
Behaviour Centred Design: towards an applied science of behaviour change
Aunger, R., & Curtis, V. (2016) · Health Psychology Review · doi:10.1080/17437199.2016.1219673 · Cited by 221
“Perceptual systems have been designed by evolution to attend to aspects of the environment that are salient – that is, those that represent something unexpected; signalling an opportunity for a reward (or a threat of a punishment) (Mnih et al., 2015; Niv et al., 2015).”
BackgroundHe, X., Yang, H., Hu, Z., & Lv, C. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3165178 · Cited by 220
Sun, Y., Peng, M., & Mao, S. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2871020 · Cited by 219
Darla Improving zero-shot transfer in reinforcement learning
Higgins, I., Pal, A., Rusu, A. A., Matthey, L., Burgess, C. P., Pritzel, A., Botvinick, M., Blundell, C., & Lerchner, A. (2017) · arXiv · doi:10.48550/arxiv.1707.08475 · Cited by 219
Self-citationSelf-Supervised Reinforcement Learning for Recommender Systems
Xin, X., Karatzoglou, A., Arapakis, I., & Jose, J. M. (2020) · Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3397271.3401147 · Cited by 219
Federated reinforcement learning: techniques, applications, and open challenges
Qi, J., Zhou, Q., Lei, L., & Zheng, K. (2021) · Intelligence & Robotics · doi:10.20517/ir.2021.02 · Cited by 218
“The control optimization problem is formulated as the MDP and a federated DDQN algorithm is developed to improve the learning performance of agents.”
MethodInfluentialOlowononi, F. O., Rawat, D. B., & Liu, C. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3036778 · Cited by 218
“Next, the deep Q-Network (DQN) [33], [34], proposed by Google DeepMind in 2013 made popular the concept of DRL.”
MethodTwo-dimensional anti-jamming communication based on deep reinforcement learning
Han, G., Xiao, L., & Poor, H. V. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952524 · Cited by 218
Flexible multitask computation in recurrent networks utilizes shared dynamical motifs
Driscoll, L., Shenoy, K., & Sussillo, D. (2022) · doi:10.1101/2022.08.15.503870 · Cited by 217
Toward the third generation artificial intelligence
Zhang, B., Zhu, J., & Su, H. (2023) · Science China Information Sciences · doi:10.1007/s11432-021-3449-x · Cited by 217
“Many achievements have been made in video games [43, 44], chess and card games [45, 46], robot navigation and control [47, 48], human-computer interaction, and other fields.”
BackgroundTowards a deliberative framework for responsible innovation in artificial intelligence
Buhmann, A., & Fieseler, C. (2021) · Technology in Society · doi:10.1016/j.techsoc.2020.101475 · Cited by 217
Multi-vehicle routing problems with soft time windows: A multi-agent reinforcement learning approach
Zhang, K., He, F., Zhang, Z., Lin, X., & Li, M. (2020) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102861 · Cited by 217
Massively parallel amplitude-only Fourier neural network
Miscuglio, M., Hu, Z., Li, S., George, J. K., Capanna, R., Dalir, H., Bardet, P. M., Gupta, P., & Sorger, V. J. (2020) · Optica · doi:10.1364/optica.408659 · Cited by 217
Battery Safety: Machine Learning-Based Prognostics
Zhao, J., Feng, X., Pang, Q., Fowler, M., Lian, Y., Ouyang, M., & Burke, A. F. (2024) · Progress in Energy and Combustion Science · doi:10.1016/j.pecs.2023.101142 · Cited by 216
Lee, J., & Mitici, M. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2022.108908 · Cited by 216
Verisig: verifying safety properties of hybrid systems with neural network controllers
Ivanov, R., Weimer, J., Alur, R., Pappas, G. J., & Lee, I. (2019) · Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control · doi:10.1145/3302504.3311806 · Cited by 216
Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs Using Proximal Policy optimization
Bohn, E., Coates, E. M., Moe, S., & Johansen, T. A. (2019) · 2019 International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2019.8798254 · Cited by 216
Agent57: Outperforming the Atari Human Benchmark
Badia, A. P., Piot, B., Kapturowski, S., Sprechmann, P., Vitvitskyi, A., Guo, D., & Blundell, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13350 · Cited by 215
Robot learning towards smart robotic manufacturing: A review
Liu, Z., Liu, Q., Xu, W., Wang, L., & Zhou, Z. (2022) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2022.102360 · Cited by 215
Zhang, R., Zong, Q., Zhang, X., Dou, L., & Tian, B. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3146976 · Cited by 215
Deep reinforcement learning in medical imaging: A literature review
Zhou, S. K., Le, H. N., Luu, K., V Nguyen, H., & Ayache, N. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102193 · Cited by 215
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.