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 1,001–1,100 of 1,418
Stochastic Activation Pruning for Robust Adversarial Defense
Dhillon, G. S., Azizzadenesheli, K., Lipton, Z. C., Bernstein, J., Kossaifi, J., Khanna, A., & Anandkumar, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.01442 · Cited by 184
Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning
Peng, B., Li, X., Gao, J., Liu, J., & Wong, K.-F. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1203 · Cited by 184
Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review
Liu, R., Nageotte, F., Zanne, P., de Mathelin, M., & Dresp-Langley, B. (2021) · Robotics · doi:10.3390/robotics10010022 · Cited by 188
“The Deep QNetwork (DQN) algorithm used with great success in [25] is the representative of this class, followed by various extensions, such as double DQN [40], Distributional DQN [41,42], etc.”
BackgroundMethodCueva, C. J., & Wei, X.-X. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.07770 · Cited by 183
“Inspired by the recent development in deep learning (Krizhevsky et al., 2012; LeCun et al., 2015; Hochreiter & Schmidhuber, 1997; Mnih et al., 2015), there has been a burst of interest in applying deep feedforward models, in particular convolutional neural networks (CNN) (LeCun et al., 1998), to…”
MethodReinforcement learning for neural architecture search: A review
Jaafra, Y., Luc Laurent, J., Deruyver, A., & Saber Naceur, M. (2019) · Image and Vision Computing · doi:10.1016/j.imavis.2019.06.005 · Cited by 183
Cao, Z., Zhou, P., Li, R., Huang, S., & Wu, D. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2968951 · Cited by 183
“For example, when DQN [34] is trained in a multiagent environment, the remaining agents become part of the environment, and the dynamic changes of other agents violate the Markov assumptions required for DQN convergence [16].”
BackgroundCephalopod Brains: An Overview of Current Knowledge to Facilitate Comparison With Vertebrates
Shigeno, S., Andrews, P. L. R., Ponte, G., & Fiorito, G. (2018) · Frontiers in Physiology · doi:10.3389/fphys.2018.00952 · Cited by 182
Lehman, J., Clune, J., Misevic, D., Adami, C., Altenberg, L., Beaulieu, J., Bentley, P. J., Bernard, S., Beslon, G., Bryson, D. M., et al. (2020) · Artificial Life · doi:10.1162/artl_a_00319 · Cited by 181
“Atari games are a common benchmark in deep reinforcement learning [94, 95, 117, 132].”
The TESCREAL bundle: Eugenics and the promise of utopia through artificial general intelligence
Gebru, T., & Torres, É. P. (2024) · First Monday · doi:10.5210/fm.v29i4.13636 · Cited by 181
Amos, B., Xu, L., & Kolter, J. Z. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.07152 · Cited by 180
Stochastic Neural Networks for Hierarchical Reinforcement Learning
Florensa, C., Duan, Y., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03012 · Cited by 180
“…years, deep reinforcement learning has achieved many impressive results, including playing Atari games from raw pixel inputs (Guo et al., 2014; Mnih et al., 2015; Schulman et al., 2015), mastering the game of Go (Silver et al., 2016), and acquiring advanced manipulation and locomotion skills…”
BackgroundTang, F., Hofner, H., Kato, N., Kaneko, K., Yamashita, Y., & Hangai, M. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126073 · Cited by 180
Machine learning for next-generation intelligent transportation systems: A survey
Yuan, T., Da Rocha Neto, W., Rothenberg, C. E., Obraczka, K., Barakat, C., & Turletti, T. (2022) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4427 · Cited by 179
“Q-Learning [57], SARSA [58], and Deep Q-Network (DQN) [59] are three typical value-based RL. Policy-based algorithms directly learn optimal policy or try to obtain an approximate optimal policy based on the observation, such as Policy Gradients (PG) [60] and Deterministic Policy Gradient (DPG) [61].”
Elallid, B. B., Benamar, N., Hafid, A. S., Rachidi, T., & Mrani, N. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.03.013 · Cited by 179
“The experimental results showed that this approach outperformed other RL approaches (Mnih et al., 2015; Lillicrap et al., 2015; Fujimoto et al., 2018; Haarnoja et al., 2018).”
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
Fang, K., Toshev, A., Fei-Fei, L., & Savarese, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00063 · Cited by 178
“We train all model variants and baselines using the standard deep Q-learning algorithm [30].”
MethodInfluentialPrivacy-preserved task offloading in mobile blockchain with deep reinforcement learning
Nguyen, D. C., Pathirana, P. N., Ding, M., & Seneviratne, A. (2020) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2020.3010967 · Cited by 178
“Fortunately, DRL methods [17] such as DQN have been introduced as a”
MethodNeural Map: Structured Memory for Deep Reinforcement Learning
Parisotto, E., & Salakhutdinov, R. (2017) · arXiv · doi:10.48550/arxiv.1702.08360 · Cited by 178
Meta-Learning with Latent Embedding Optimization
Rusu, A. A., Rao, D., Sygnowski, J., Vinyals, O., Pascanu, R., Osindero, S., & Hadsell, R. T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.05960 · Cited by 178
Self-citationSurvey on reinforcement learning for language processing
Uc-Cetina, V., Navarro-Guerrero, N., Martin-Gonzalez, A., Weber, C., & Wermter, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10205-5 · Cited by 177
“We believe that such limitation could be overcome with continuous state space representations and the use of function approximation techniques such as DQN (Mnih et al. 2015), VIN (Tamar et al.”
MethodInfluentialLearning to Optimize Tensor Programs
Chen, T., Zheng, L., Yan, E., Jiang, Z., Moreau, T., Ceze, L., Guestrin, C., & Krishnamurthy, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08166 · Cited by 177
RL/DRL Meets Vehicular Task Offloading Using Edge and Vehicular Cloudlet: A Survey
Liu, J., Ahmed, M., Mirza, M. A., Khan, W. U., Xu, D., Li, J., Aziz, A., & Han, Z. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3155667 · Cited by 176
Reinforcement learning for electric vehicle applications in power systems:A critical review
Qiu, D., Wang, Y., Hua, W., & Strbac, G. (2023) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2022.113052 · Cited by 176
Skin disease diagnosis with deep learning: a review
Li, H., Pan, Y., Zhao, J., & Zhang, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.096 · Cited by 178
Shared Autonomy via Deep Reinforcement Learning
Reddy, S., Dragan, A., & Levine, S. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.005 · Cited by 175
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
Plappert, M., Andrychowicz, M., Ray, A., McGrew, B., Baker, B., Powell, G., Schneider, J., Tobin, J., Chociej, M., Welinder, P., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09464 · Cited by 175
“Faster information propagation Most state-of-the-art off-policy RL algorithms use target networks to stabilize training (e.g. DQN (Mnih et al., 2015) or DDPG (Lillicrap et al., 2015)).”
BackgroundMethodSurvey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods
Cao, Y., Zhao, H., Cheng, Y., Shu, T., Chen, Y., Liu, G., Liang, G., Zhao, J., Yan, J., & Li, Y. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3497992 · Cited by 174
“2) Challenges of RL: While RL algorithms have made remarkable performance in recent years [2], [7], [49], there are still several longstanding challenges that limit the real-world applicability of RL. 1) Generalization in Unseen Environment: Generalization in unseen environments remains a…”
Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning
Anderson, H. S., Kharkar, A., Filar, B., Evans, D., & Roth, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.08917 · Cited by 174
Q-PrOP: Sample-efficient policy gradient with an off-policy critic
Gu, S., Lillicrap, T., Ghahramani, Z., Turner, R. E., & Levine, S. (2016) · arXiv (Cornell University) · doi:10.17863/cam.21294 · Cited by 174
Santana, E., & Hotz, G. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.01230 · Cited by 174
“Vision based controls and reinforcement learning had recent success in the literature [7] [8] [9] [10] mostly due to (deep, recurrent) neural networks and unbounded access to world or game iteraction.”
BackgroundMethodLearning agile soccer skills for a bipedal robot with deep reinforcement learning
Haarnoja, T., Moran, B., Lever, G., Huang, S. H., Tirumala, D., Humplik, J., Wulfmeier, M., Tunyasuvunakool, S., Siegel, N. Y., Hafner, R., et al. (2024) · Science Robotics · doi:10.1126/scirobotics.adi8022 · Cited by 173
A survey on multi-agent reinforcement learning and its application
Ning, Z., & Xie, L. (2024) · Journal of Automation and Intelligence · doi:10.1016/j.jai.2024.02.003 · Cited by 173
Loss of plasticity in deep continual learning
Dohare, S., Hernandez-Garcia, J. F., Lan, Q., Rahman, P., Mahmood, A. R., & Sutton, R. S. (2024) · Nature · doi:10.1038/s41586-024-07711-7 · Cited by 172
“Machine learning and artificial intelligence have made remarkable progress in the past decade, with landmark successes in natural-language processing 2,3 , biology 4 , game playing 5–8 and robotics 9,10 .”
Mocanu, E., Nguyen, P. H., Kling, W. L., & Gibescu, M. (2016) · Energy and Buildings · doi:10.1016/j.enbuild.2016.01.030 · Cited by 171
Meta-learning in natural and artificial intelligence
Wang, J. X. (2021) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2021.01.002 · Cited by 171
A Berkeley View of Systems Challenges for AI
Stoica, I., Song, D., Popa, R. A., Patterson, D., Mahoney, M. W., Katz, R., Joseph, A. D., Jordan, M., Hellerstein, J. M., Gonzalez, J. E., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.05855 · Cited by 171
“for each application. Recent e‡orts are combining deep neural networks with RL (Deep RL) to develop more robust training algorithms that can work for a variety of environments (e.g., many Atari games [77]), or even across di‡erent application domains, as in the control of (simulated) robots [92] and the learning of ro…”
BackgroundAttention, Learn to Solve Routing Problems!
Kool, W., van Hoof, H., & Welling, M. (2018) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.1803.08475 · Cited by 171
“…predictions, Reinforcement Learning (RL) has enabled algorithms to learn to make decisions, either by interaction with an environment to learn to play Atari games (Mnih et al., 2015), or by inducing knowledge through look-ahead search: this was used to master the game of Go (Silver et al., 2017).”
MethodInfluentialEquivalence Between Policy Gradients and Soft Q-Learning
Schulman, J., Chen, X., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.06440 · Cited by 171
“Altogether, the update matches what is typically done in “actor-critic” policy gradient methods such as A3C, which explains why Mnih et al. [2016] obtained qualitatively similar results from policy gradients and n-step Q-learning.”
MethodResultInfluentialChallenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
Ilahi, I., Usama, M., Qadir, J., Janjua, M. U., Al-Fuqaha, A., Hoang, D. T., & Niyato, D. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3111139 · Cited by 170
Never Give Up: Learning Directed Exploration Strategies
Badia, A. P., Sprechmann, P., Vitvitskyi, A., Guo, D., Piot, B., Kapturowski, S., Tieleman, O., Arjovsky, M., Pritzel, A., Bolt, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2002.06038 · Cited by 170
Sayed, W. S., Noeman, A. M., Abdellatif, A., Abdelrazek, M., Badawy, M. G., Hamed, A., & El-Tantawy, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13076-8 · Cited by 169
Ablation Studies in Artificial Neural Networks
Meyes, R., Lu, M., de Puiseau, C. W., & Meisen, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08644 · Cited by 168
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
Omidshafiei, S., Pazis, J., Amato, C., How, J. P., & Vian, J. L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06182 · Cited by 168
“Target network parameters ˆ θ j are updated less frequently and, in combination with experience replay, are critical for stable deep Q-learning.”
MethodInfluentialD-DASH: A Deep Q-Learning Framework for DASH Video Streaming
Gadaleta, M., Chiariotti, F., Rossi, M., & Zanella, A. (2017) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2017.2755007 · Cited by 168
“This leads to three main advantages: greater data efficiency, uncorrelated subsequent training samples and independence between current policy and samples [44].”
BackgroundMethodInfluentialLi, W. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2024.2310354 · Cited by 167
“This technology permeates various industries, underscoring the importance of understanding and harnessing its potential and challenges for driving future innovations (Mnih et al., 2015).”
Reinforcement Learning for Solving the Vehicle Routing Problem
Nazari, M., Oroojlooy, A., Snyder, L., & Takáč, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04240 · Cited by 167
“iveness and generality of their architecture. On a related topic,Dai et al.(2017) solve optimization problems over graphs with using a graph embedding structure (Dai et al.,2016) and a DQN algorithm (Mnih et al., 2015). Even though VRP can be represented by a graph with weighted nodes and edges, their proposed model d…”
MethodFast Context Adaptation via Meta-Learning
Zintgraf, L., Shiarlis, K., Kurin, V., Hofmann, K., & Whiteson, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.03642 · Cited by 167
Meta-Reinforcement Learning of Structured Exploration Strategies
Gupta, A., Mendonca, R., Liu, Y., Abbeel, P., & Levine, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.07245 · Cited by 166
“Deep reinforcement learning methods have been shown to learn complex tasks ranging from games (Mnih et al., 2015) to robotic control (Levine et al., 2016; Lillicrap et al., 2015) with minimal supervision, by simply exploring the environment and experiencing rewards.”
BackgroundEmotion in reinforcement learning agents and robots: a survey
Moerland, T. M., Broekens, J., & Jonker, C. M. (2018) · Machine Learning · doi:10.1007/s10994-017-5666-0 · Cited by 205
“Potentially, the advances in solving more complex AI scenarios with (deep) RL (Silver et al, 2016; Mnih et al, 2015) may provide more realistic test scenarios in the future as well.”
BackgroundInfluentialLearning Invariant Representations for Reinforcement Learning without Reconstruction
Zhang, A., McAllister, R., Calandra, R., Gal, Y., & Levine, S. (2020) · arXiv · doi:10.48550/arxiv.2006.10742 · Cited by 165
Deep reinforcement learning based control for Autonomous Vehicles in CARLA
Pérez-Gil, Ó., Barea, R., López-Guillén, E., Bergasa, L. M., Gómez-Huélamo, C., Gutiérrez, R., & Díaz-Díaz, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11437-3 · Cited by 165
“…Processes (MDPs), where the scope of the algorithm is to calculate the optimal policy of an agent to choose actions in an environment with the goal of maximize a reward function, obtaining quite successful results in fields like solving computer games [42] or simple decision-making system [35].”
BackgroundDeep Reinforcement Learning with a Natural Language Action Space
He, J., Chen, J., He, X., Gao, J., Li, L., Deng, L., & Ostendorf, M. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1153 · Cited by 164
“All methods are initialized with small random weights, so initial Q-value differences will be small, thus making the Q-learning algorithm more explorative initially.”
BackgroundMethodInfluentialMeta-Gradient Reinforcement Learning
Xu, Z., van Hasselt, H. P., & Silver, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.09801 · Cited by 164
“…functions of the return, including, for instance, value-based methods like SARSA( λ ) [Rummery and Niranjan, 1994, Sutton and Barto, 2018] and DQN [Mnih et al., 2015], policy-gradient methods [Williams, 1992], or actor-critic algorithms like A3C [Mnih et al., 2016] and IMPALA [Espeholt et al.,…”
BackgroundMethodInfluentialSelf-citationMobile-robotic machining for large complex components: A review study
Tao, B., Zhao, X., & Ding, H. (2019) · Science China Technological Sciences · doi:10.1007/s11431-019-9510-1 · Cited by 164
Wind Turbine Blade Breakage Monitoring With Deep Autoencoders
Wang, L., Zhang, Z., Xu, J., & Liu, R. (2018) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2016.2621135 · Cited by 163
Blundell, C., Uria, B., Pritzel, A., Li, Y., Ruderman, A., Leibo, J. Z., Rae, J., Wierstra, D., & Hassabis, D. (2016) · arXiv · doi:10.48550/arxiv.1606.04460 · Cited by 162
Self-citationDeep learning in computational mechanics: a review
Herrmann, L., & Kollmannsberger, S. (2024) · Computational Mechanics · doi:10.1007/s00466-023-02434-4 · Cited by 162
“Reinforcement learning has achieved impressive results such as human-level performance in games like Atari [580], Go [581], and StarCraft II [582].”
Deep Reinforcement Learning for Mobile Edge Caching: Review, New Features, and Open Issues
Zhu, H., Cao, Y., Wang, W., Jiang, T., & Jin, S. (2018) · IEEE Network · doi:10.1109/mnet.2018.1800109 · Cited by 153
Deep learning for signal authentication and security in massive internet-of-things systems
Ferdowsi, A., & Saad, W. (2019) · IEEE Transactions on Communications · doi:10.1109/tcomm.2018.2878025 · Cited by 160
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Chatzilygeroudis, K., Vassiliades, V., Stulp, F., Calinon, S., & Mouret, J.-B. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2958211 · Cited by 160
Augmented Language Models: a Survey
Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., Celikyilmaz, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.07842 · Cited by 160
“…for learning complex behaviors through feedback-based interaction with an environment, and it has been used for applications such as playing games (Mnih et al., 2015; Silver et al., 2016; Vinyals et al., 2019; Team et al., 2021; Bakhtin et al., 2022) or controlling robots (Gu et al., 2017;…”
BackgroundMethodLearning structures: Predictive representations, replay, and generalization
Momennejad, I. (2020) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2020.02.017 · Cited by 159
Mapping Spiking Neural Networks to Neuromorphic Hardware
Balaji, A., Catthoor, F., Das, A., Wu, Y., Huynh, K., Dell'Anna, F. G., Indiveri, G., Krichmar, J. L., Dutt, N. D., & Schaafsma, S. (2020) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2019.2951493 · Cited by 159
“Examples include the liquid state machine [27], zero-shot learning [61], one-shot learning [62], lifelong learning [63], transfer learning [64], and deep reinforcement learning [65] among others.”
BackgroundExploratory Combinatorial Optimization with Reinforcement Learning
Barrett, T., Clements, W., Foerster, J., & Lvovsky, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5723 · Cited by 159
TROVE: A Context-Awareness Trust Model for VANETs Using Reinforcement Learning
Guo, J., Li, X., Liu, Z., Ma, J., Yang, C., Zhang, J., & Wu, D. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2975084 · Cited by 159
“The Q -learning algorithm was proposed by DeepMind [36], [37] and used to deal with the continuous strategy optimization.”
MethodWho Gets Credit for AI-Generated Art?
Epstein, Z., Levine, S., Rand, D. G., & Rahwan, I. (2020) · iScience · doi:10.1016/j.isci.2020.101515 · Cited by 157
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Peng, X. B., Kumar, A., Zhang, G., & Levine, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.00177 · Cited by 158
“queue, as is common for off-policy reinforcement learning algorithms (Mnih et al., 2015; Lillicrap et al., 2016).”
BackgroundMethodInfluentialStrategy in the Age of Artificial Intelligence
Ayoub, K., & Payne, K. (2016) · Journal of Strategic Studies · doi:10.1080/01402390.2015.1088838 · Cited by 158
“35 The machine ’ s task was to repeatedly play each Atari game to maximise its reward, de fi ned as the score in the game.”
MethodSynchronisation through learning for two self-propelled swimmers
Novati, G., Verma, S., Alexeev, D., Rossinelli, D., van Rees, W. M., & Koumoutsakos, P. (2017) · Bioinspiration & Biomimetics · doi:10.1088/1748-3190/aa6311 · Cited by 157
“An important aspect of this work is that the swimmer learns a parameterized approximation of Q(s, a) by training a Neural Network with experience replay [23].”
BackgroundLTL and Beyond: Formal Languages for Reward Function Specification in Reinforcement Learning
Camacho, A., Toro Icarte, R., Klassen, T. Q., Valenzano, R., & McIlraith, S. A. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/840 · Cited by 157
Deep Reinforcement Learning based Resource Allocation in Low Latency Edge Computing Networks
Yang, T., Hu, Y., Gursoy, M. C., Schmeink, A., & Mathar, R. (2018) · 2018 15th International Symposium on Wireless Communication Systems (ISWCS) · doi:10.1109/iswcs.2018.8491089 · Cited by 156
Modeling Avoidance in Mood and Anxiety Disorders Using Reinforcement Learning
Mkrtchian, A., Aylward, J., Dayan, P., Roiser, J. P., & Robinson, O. J. (2017) · Biological Psychiatry · doi:10.1016/j.biopsych.2017.01.017 · Cited by 151
“Reinforcement learning algorithms can provide parameterizations of avoidance behavior that offer insight into both optimal behavior when set correctly (17) and to dysfunction and pathology when set incorrectly (18).”
Chu, M., Li, H., Liao, X., & Cui, S. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2872440 · Cited by 153
A multi-objective deep reinforcement learning framework
Nguyen, T. T., Nguyen, N. D., Vamplew, P., Nahavandi, S., Dazeley, R., & Lim, C. P. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103915 · Cited by 152
Dynamic Zoom-in Network for Fast Object Detection in Large Images
Gao, M., Yu, R., Li, A., Morariu, V. I., & Davis, L. S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00724 · Cited by 148
Sadeghianpourhamami, N., Deleu, J., & Develder, C. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2019.2920320 · Cited by 150
Empiricism without magic: transformational abstraction in deep convolutional neural networks
Buckner, C. (2018) · Synthese · doi:10.1007/s11229-018-01949-1 · Cited by 149
Transferring policy of deep reinforcement learning from simulation to reality for robotics
Ju, H., Juan, R., Gomez, R., Nakamura, K., & Li, G. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00573-6 · Cited by 147
Towards Deep Symbolic Reinforcement Learning
Garnelo, M., Arulkumaran, K., & Shanahan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05518 · Cited by 146
“In a conventional DRL system, such as DQN [4], this is achieved through the generalising capabilities of the neural network that approximates the Q function (or the value function or policy function, depending on the style of reinforcement learning in question).”
BackgroundMethodPerreault Levasseur, L., Hezaveh, Y. D., & Wechsler, R. H. (2017) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/aa9704 · Cited by 145
“These networks have exceeded human performance in many experiments, including competing against a Go champion (Silver et al. 2016), playing Atari games (Mnih et al. 2015), and outperforming practicing dermatologists in the visual diagnosis of skin cancer (Esteva et al. 2017).”
BackgroundOptimizing Task Scheduling in Human-Robot Collaboration with Deep Multi-Agent Reinforcement Learning
Yu, T., Huang, J., & Chang, Q. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.07.015 · Cited by 143
Motion Planning for Mobile Robots—Focusing on Deep Reinforcement Learning: A Systematic Review
Sun, H., Zhang, W., Yu, R., & Zhang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3076530 · Cited by 143
Prediction error, ketamine and psychosis: An updated model
Corlett, P. R., Honey, G. D., & Fletcher, P. C. (2016) · Journal of Psychopharmacology · doi:10.1177/0269881116650087 · Cited by 142
“…architectures comprised of many Hopfield networks, separated by hidden layers, that learn representations of data without supervision and use reinforcement learning on these representations to guide action selection, beating humans at Atari games (Mnih et al., 2015) and Go (Silver et al., 2016).”
BackgroundDeep Reinforcement Learning at the Edge of the Statistical Precipice
Agarwal, R., Schwarzer, M., Castro, P. S., Courville, A., & Bellemare, M. G. (2021) · arXiv · doi:10.48550/arxiv.2108.13264 · Cited by 142
Self-citationAdaptive Quantitative Trading: An Imitative Deep Reinforcement Learning Approach
Liu, Y., Liu, Q., Zhao, H., Pan, Z., & Liu, C. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i02.5587 · Cited by 141
“DRL has achieved great strides in complex tasks, such as video games (Mnih et al. 2015).”
BackgroundSoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
Lin, X., Wang, Y., Olkin, J., & Held, D. (2020) · arXiv · doi:10.48550/arxiv.2011.07215 · Cited by 140
A Human-AI Collaborative Approach for Clinical Decision Making on Rehabilitation Assessment
Lee, M. H., Siewiorek, D. P., Smailagic, A., Bernardino, A., & Bermúdez i Badia, S. B. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445472 · Cited by 137
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
Deng, Y., Li, Y., Sun, F., Ding, B., & Lam, W. (2021) · Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3404835.3462913 · Cited by 136
Zhu, H., Goh, H. H., Zhang, D., Ahmad, T., Liu, H., Wang, S., Li, S., Liu, T., Dai, H., & Wu, T. (2022) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2021.129809 · Cited by 131
Model-Free Quantum Control with Reinforcement Learning
Sivak, V. V., Eickbusch, A., Liu, H., Royer, B., Tsioutsios, I., & Devoret, M. H. (2022) · Physical Review X · doi:10.1103/physrevx.12.011059 · Cited by 130
“We expect that in the limit of infinite averaging, the training would proceed as if the fidelity F was directly available to be used as a reward (blue line).”
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Hutsebaut-Buysse, M., Mets, K., & Latré, S. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4010009 · Cited by 129
“For example, the DQN algorithm [8], and more recently PPO [11] Rainbow [12], and Atari57 [13] are RL algorithms that are capable of achieving above human-level performance on a set of classic Atari 2600 video games.”
BackgroundMethodResultInfluentialSpecialized Deep Neural Networks for Battery Health Prognostics: Opportunities and Challenges
Zhao, J., Han, X., Ouyang, M., & Burke, A. F. (2023) · Journal of Energy Chemistry · doi:10.1016/j.jechem.2023.08.047 · Cited by 129
Robot Learning From Randomized Simulations: A Review
Muratore, F., Ramos, F., Turk, G., Yu, W., Gienger, M., & Peters, J. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.799893 · Cited by 128
“, 2012) and games (Mnih et al., 2015; Silver et al., 2016), the question arises why we do not see similar results in robotics.”
ResultWang, Z., Novikov, A., Zolna, K., Springenberg, J. T., Reed, S., Shahriari, B., Siegel, N., Merel, J., Gulcehre, C., Heess, N., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.15134 · Cited by 128
“where the expectation over data is approximated by sampling (st,at, rt, st+1) ⇠ B and D is some divergence measure; measuring discrepancy between the current estimate of the action-value Q✓(st,at) (for policy ⇡) and the td-update, based on a target network [24].”
BackgroundEvaluation of advanced control strategies for building energy systems
Stoffel, P., Maier, L., Kümpel, A., Schreiber, T., & Müller, D. (2023) · Energy and Buildings · doi:10.1016/j.enbuild.2022.112709 · Cited by 126
“…more design principles and innovations from the field of RL are being published, and state-of-the-art algorithms, like the Deep Q-Networks (DQN) ([70]) for discrete control actions or the Soft-Actor-Critic (SAC) for continuous control actions, can quickly find a good and finally optimal control…”
Navigating to objects in the real world
Gervet, T., Chintala, S., Batra, D., Malik, J., & Chaplot, D. S. (2023) · Science Robotics · doi:10.1126/scirobotics.adf6991 · Cited by 125
“Inspired by seminal proofs of concept in autonomous driving [26, 27] and early successes of pixel-to-action deep reinforcement learning [28, 29], early applications of end-to-end learning to semantic navigation include [30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40].”
BackgroundDecoupling Representation Learning from Reinforcement Learning
Stooke, A., Lee, K., Abbeel, P., & Laskin, M. (2020) · arXiv · doi:10.48550/arxiv.2009.08319 · Cited by 123
A Deep Actor-Critic Reinforcement Learning Framework for Dynamic Multichannel Access
Zhong, C., Lu, Z., Gursoy, M. C., & Velipasalar, S. (2019) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2019.2952909 · Cited by 123
“Inspired by the achievements of reinforcement learning in dynamic control problems, such as the game of Atari [16], and AlphaGo [17], there has been increased interest in seeking reinforcement learning based solutions for problems in wireless communications.”
BackgroundIndicators and criteria of consciousness in animals and intelligent machines: an inside-out approach
Pennartz, C. M. A., Farisco, M., & Evers, K. (2019) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2019.00025 · Cited by 121
“Current reinforcement learning-based networks are capable of supra-human performance on Alpha-Go (Silver et al., 2017) and have been shown to learn 40 computer games simultaneously (Mnih et al., 2015).”
Dark control: The default mode network as a reinforcement learning agent
Dohmatob, E., Dumas, G., & Bzdok, D. (2020) · Human Brain Mapping · doi:10.1002/hbm.25019 · Cited by 121
“…representation of the state-action pairs ( s, a ), as was previously proposed (Song et al., 2016), or artificial neural-network models as demonstrated in seminal machine-learning models (Mnih et al., 2015; Silver et al., 2016) for playing complex games (atari, Go, etc.) at super-human levels.”
BackgroundMethodInfluentialBiferale, L., Bonaccorso, F., Buzzicotti, M., Clark Di Leoni, P., & Gustavsson, K. (2019) · Chaos: An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.5120370 · Cited by 121
“[54] V.”
Method
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.