Cited by 528Reinforcement Learning in RoboticsAdvanced Bandit Algorithms ResearchArtificial Intelligence in Games

The DOI matches its Crossref record; 185 of the 185 references it cites were found in a registry or an index.

Exploration in deep reinforcement learning: A survey

Open access

Ladosz, Pawel, Weng, Lilian, Kim, Minwoo, Oh, Hyondong·2022·Information Fusion

DOI 10.1016/j.inffus.2022.03.003

Open this paper in CoChat — free account Open PDF

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1016/j.inffus.2022.03.003

Cites

185 of 185 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 1×
“impressive performance in Atari games [2], Mujoco simulator [3], controllers tuning [4], autonomous landing [5], self-driving cars [6] and healthcare [7].”
Background
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 · cited 1×
“The most common technique for exploration in reinforcement learning is random exploration [1].”
Method
Generative Adversarial Nets
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,119
Proceedings of IEEE International Conference on Computer Vision
(1995) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1995.466933 · Cited by 13,117
Proceedings of the 24th international conference on Machine learning
(2007) · doi:10.1145/1273496 · Cited by 11,869
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 1×
“impressive performance in Atari games [2], Mujoco simulator [3], controllers tuning [4], autonomous landing [5], self-driving cars [6] and healthcare [7].”
Background
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
Williams, R. J. (1992) · Machine Learning · doi:10.1007/bf00992696 · Cited by 8,608
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767
Deep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733 · cited 1×
“A general overview of reinforcement learning can be found in [23].”
Background
Proceedings. 1985 IEEE International Conference on Robotics and Automation
(1985) · doi:10.1109/robot.1985 · Cited by 3,692

Show all 185 references

Research works printed but not linked: 1

T. Gangwani, Q. Liu, J. Peng, Learning Self-Imitating Diverse Policies, in: 7th International Conference on Learning Representations, ICLR 2019, 2019.

Sorted by citations

Items 201–300 of 528

A Synergistic MOEA Algorithm with GANs for Complex Data Analysis
Qian, W., Xu, H., Chen, H., Yang, L., Lin, Y., Xu, R., Yang, M., & Liao, M. (2024) · Mathematics · doi:10.3390/math12020175 · Cited by 4
Entertainment robots based on digital new media application in real-time error correction mode for Chinese English translation
Geng, Y. (2024) · Entertainment Computing · doi:10.1016/j.entcom.2024.100789 · Cited by 4
Adversarial Training With Anti-Adversaries
Zhou, X., Wu, O., & Yang, N. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3432973 · Cited by 14
“Reinforcement Learning: Reinforcement learning [32], [33], [34] studies how natural and artiﬁcial systems learn to predict consequences and optimize their behavior in the environment from one state/situation to another.”
Background
Deep Q-learning Network-based Imbalanced Classification for Fatality Prediction of Single-Vehicle Motorcycle Crashes
Zulherman, D., Yang, J., Shimizu, K., & Yokota, Y. (2024) · International Journal of Intelligent Transportation Systems Research · doi:10.1007/s13177-024-00440-1 · Cited by 4
GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
Zhou, Z., Xie, X., Song, J., Shu, Z., & Ma, L. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3496492 · Cited by 4
“During the progression toward an optimal policy, the agent may exhibit numerous unsafe intermediate policies, posing risks not only to the system itself but also to its surrounding environment [5].”
Multi-agent Reinforcement Learning for Dynamic Dispatching in Material Handling Systems
Lee, X. Y., Wang, H., KATSUMATA, D., Matsui, T., & Gupta, C. (2024) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi62246.2024.00031 · Cited by 4
“…have been explored in works which leverages expert demonstrations [Ramírez et al., 2022] and there are also numerous heuristic-agnostic methods that focus on improving exploration, such as the methods discussed in the following works by Ladosz et al. [2022], Yang et al. [2021], Hao et al. [2023].”
Adaptive Path Planning for Amphibious Vehicles Based on Enhanced Hybrid A-Star Algorithm
Song, R., Chen, T., Pan, J., & Peng, Y. (2024) · International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE) · doi:10.1109/icemce64157.2024.10862721 · Cited by 4
Curriculum Learning Algorithms for Reward Weighting in Sparse Reward Robotic Manipulation Tasks
Fele, B., & Babič, J. (2025) · IEEE Access · doi:10.1109/access.2025.3549639 · Cited by 4
“…where the reward provides a gradient indicating better and worse solutions, sparse rewards are only informative once the task has been successfully completed, requiring increasingly more exploration depending on the specificity of the solution and the size of the state and action space [1].”
An efficient dynamic energy replenishment and data gathering strategy based on deep reinforcement learning in wireless rechargeable sensor networks
Zhao, M., Li, J., Chai, X., & Li, J. (2025) · Alexandria Engineering Journal · doi:10.1016/j.aej.2025.03.069 · Cited by 4
Collision-inducing method for UAV evasive maneuvers based on receding horizon optimization
Tang, H., Tang, Z., Chen, G., & Guo, J. (2025) · Defence Technology · doi:10.1016/j.dt.2025.04.001 · Cited by 4
Towards the portability of knowledge in reinforcement learning-based systems for automatic drone navigation
Barreiro, J. M., Lara, J. A., Manrique, D., & Smith, P. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1402 · Cited by 4
Comparing Artificial Intelligence Classification Models to Improve an Image Comparison System with User Inputs
Jardim, S., Valente, J., Almeida, A., & Mora, C. (2023) · SN Computer Science · doi:10.1007/s42979-023-02375-y · Cited by 4
“The behavior of the Markov Decision Process is usually determined by a reward function [31], whereby an agent is given a state and a reward from the environment, which is used to determine the appropriate action to take [17, 20, 28, 31].”
Background
Whittle Index Based User Association in Dense Millimeter Wave Networks
Nalavade, M. R., Kasbekar, G. S., & Borkar, V. S. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3528456 · Cited by 4
“As a result, good rewards may be encountered infrequently, making it challenging for the agent to learn an effective value function or policy [51]. iv) Training neural networks in DRL is prone to instability due to vanishing/ exploding gradients and the non-stationarity of environments.”
Multi-Agent Reinforcement Learning for Providing Flexibility Services in Local Energy Communities
Afzali, S., Alizadeh, M., Zamani, R., & Moghaddam, M. P. (2024) · International Conference on Technology and Energy Management (ICTEM) · doi:10.1109/ictem60690.2024.10632029 · Cited by 3
“The agent’s objective is to learn an optimal policy that maximizes the cumulative reward over time [21].”
Background
Deep Reinforcement Learning-Guided Inverse Design of Transparent Heat Mirror Film for Broadband Spectral Selectivity
Zeng, Z., Ji, H., Xiao, T., Peng, L., Liu, B., Jin, S., & Cao, Y. (2025) · Materials · doi:10.3390/ma18122677 · Cited by 3
“Deep reinforcement learning (DRL) combines the feature extraction capability of deep learning with the decision-making ability of reinforcement learning [26–28] and has emerged as one of the most prominent research directions in machine learning [29].”
Permutation-Invariant and Equivariant Multiagent Reinforcement Learning for Flexible Manufacturing in Industrial IoT
Zeng, Y., Liu, A., Huang, S., Chen, X., Liang, W., & Zhou, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3584811 · Cited by 4
“In recent years, deep reinforcement learning (DRL) [12] has surfaced as a potent approach for addressing intricate decision-making challenges, providing the capability to derive optimal strategies directly from data.”
Iterative Learning Predictive Control Method Based on Reinforcement Learning for Rubber Mixing Batch Process
He, W., Pan, Y., & Bo, C. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3591540 · Cited by 3
“It has gained widespread attention and demonstrated superior performance in Artiﬁcial Intelligence (AI) domains such as autonomous driving [24], game simulators [25], and manufacturing robotic tasks [26], [27].”
Sample-efficient multi-objective reinforcement learning for hybrid impulsive information consensus in multi-agent systems
Gu, Y., Liang, Z., Wu, S., Tao, Y., Zhao, C., & Xu, R. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122791 · Cited by 3
Enhancing environmental modeling and maximum diffusion reinforcement learning using evolutionary computation for optimal performance
Zhao, Y., & Pei, Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.114111 · Cited by 3
Hybrid functional 3D artificial synapses for convolution and reinforcement learning
Im, J., Kim, J., Ko, J., Shin, W., Koo, R., Kim, J., & Lee, J. (2025) · Science Advances · doi:10.1126/sciadv.adw7498 · Cited by 3
UAV exploration for indoor navigation based on deep reinforcement learning and intrinsic curiosity
Lin, H.-Y., Zhang, X.-S., & Munir, S. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200618 · Cited by 3
Network Recovery From Cascading Failures in Cyber–Service-Coupled Manufacturing Internet of Things
Qian, J., Fu, X., Xing, L., & Peng, R. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3652229 · Cited by 3
“Speciﬁcally, following related research [26], [41], we set the candidate values for the learning rate α as { 1 × 10 − 5 , 1 × 10 − 4 , and 1 × 10 − 3 } and for the mini-batch size B as { 32, 64, 128 } .”
Robust robotic assembly via hierarchical diffusion policy-guided reinforcement learning
Zhou, Y., Li, X., Yin, Y., Chen, L., Xu, H., Fu, J., Zhou, A., & Yi, J. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104399 · Cited by 3
ASS-DQN: A deep reinforcement learning approach for path planning in multi-machine cooperative operations
Xiang, R., Ma, P., Gong, L., Tian, M., Li, R., Fei, H., & Yi, H. (2026) · Smart Agricultural Technology · doi:10.1016/j.atech.2026.101887 · Cited by 3
Energy Management Strategies for Fuel Cell Hybrid Ships: Classification, Comparison, and Outlook
Bai, M., Ke, W., Wu, C., Cheng, H., Zhang, J., & Yang, X. (2026) · Energies · doi:10.3390/en19051171 · Cited by 3
Evolutionary dynamics under combined regret-based learning and random exploration
Zhu, M., Xu, J., Chen, X., & Szolnoki, A. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.118289 · Cited by 3
Integrated resource scheduling and delivery in construction using autonomous mobile robots and enhanced 6-DoF grasping
Lin, F., Li, M., Wang, B., Chen, Z., Zhang, X., & Cheng, J. C. P. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.106968 · Cited by 3
Navigation and Sensor Fusion for Autonomous Field Robots in Precision Agriculture: Narrative Review
Boros, N., Ambrus, B., & Nyéki, A. (2026) · Sensors · doi:10.3390/s26165169 · Cited by 3
“Deep-learning approaches can also adapt to complex, dynamic environments [49,50].”
ASTPSI: Allocating Spare Time and Planning Speed Interval for Intelligent Train Control of Sparse Reward
Zhang, H., & Xian, G. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8079-6_6 · Cited by 3
An Intelligent Routing Approach for SDN Based on Improved DuelingDQN Algorithm
Wang, J., Zhou, T., Liu, Z., & Zhu, J. (2023) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc59590.2023.10507555 · Cited by 3
“…monitors the topology information and link state through the controller, explores and utilizes decision making using reinforcement learning [12] to obtain the optimal forwarding paths between the source node and the destination node, and carries out the adaptive adjustment of the network…”
Background
An evolutionary knowledge transfer framework for solving workgroup reconfiguration problem in aircraft final assembly
Cai, H., Ye, Q., Zhao, Q., & Liu, L. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111959 · Cited by 3
A NoisyNet deep reinforcement learning method for frequency regulation in power systems
Zhang, B., Iu, H. H., Zhang, X., & Chau, T. K. (2024) · IET Generation Transmission & Distribution · doi:10.1049/gtd2.13250 · Cited by 3
Deep Reinforcement Learning-Enhanced Target Encirclement of Multiple Unmanned Surface Vessels
Yang, C., Liu, J., Cai, X., Wei, W., & Ge, M. (2024) · Unmanned Systems · doi:10.1142/s2301385025410055 · Cited by 3
An optimized task offloading strategy based on deep reinforcement learning combined with channel reliability prediction
Tang, W., Yang, Y., Gao, D., Chen, J., Huang, S., & Chen, N. (2024) · Wireless Networks · doi:10.1007/s11276-024-03838-7 · Cited by 3
“Reinforcement learning is generally used to solve MDP, but this paper uses DRL [6] to solve MDP.”
Multi-dimensional requirements for reinforcement recommendation reasoning
Li, Y., Tong, X., & Lv, Z. (2025) · Applied Intelligence · doi:10.1007/s10489-024-05854-8 · Cited by 3
“Recently, the rise of deep reinforcement learning (DRL) has brought a new solution for recommendation systems [6–9].”
Adaptive English vocabulary recommendation systems: a computational intelligence approach using deep reinforcement learning
Zhang, T., & Li, C. (2025) · International Conference on Big Data, Computational Intelligence, and Applications (BDCIA) · doi:10.1117/12.3059790 · Cited by 3
“Machine learning models trained on fixed datasets struggle to generalize effectively, particularly when applied to diverse user populations or new learning contexts [11].”
Dynamic data partitioning strategy for distributed learning on heterogeneous edge system
Yu, K., & Zhang, W. (2025) · Computer Communications · doi:10.1016/j.comcom.2025.108262 · Cited by 3
Optimized Feature Extraction for Sample Efficient Deep Reinforcement Learning
Li, Y., Guo, T., Li, Q., & Liu, X. (2023) · Electronics · doi:10.3390/electronics12163508 · Cited by 4
“The crux of the sample inefficiency quandary lies in achieving a delicate equilibrium between exploring and exploiting the active quest for uncharted states and behaviors that hold the promise of yielding elevated rewards and long-term gains [9], juxtaposed against the knowledge acquired thus far to maximize instantan…”
Background
A Fast Anti-Jamming Algorithm Based on Imitation Learning for WSN
Zhou, W., Zhou, Z., Niu, Y., Zhou, Q., & Ding, H. (2023) · Sensors · doi:10.3390/s23229240 · Cited by 3
“…state–action space, the “curse of dimensionality” problem faced by reinforcement learning leads to signiﬁcantly increased convergence time and even difﬁculty in convergence [14], which severely affects the feasibility of such algorithms in the time-varying environments of wireless sensor networks.”
Background
Engineering AI for provable retention of objectives over time
Fasoro, S. A. (2024) · AI Magazine · doi:10.1002/aaai.12167 · Cited by 3
Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
Park, J., Kim, Y., Yoo, H. B., Lee, M. W., Kim, K., Choi, W.-S., Lee, M., & Zhang, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i1.27815 · Cited by 3
Harnessing traditional controllers for fast-track training of deep reinforcement learning control strategies
Alam, M. S., & Carlucho, I. (2024) · Journal of Marine Engineering & Technology · doi:10.1080/20464177.2024.2367276 · Cited by 3
“However, it is essential to acknowledge that the computational demands of training these algorithms are substantial (Ladosz et al. 2022).”
Reinforcement Learning in Social Sciences: A Survey
El-Shahat, D., Talal, N., & Abouhawwash, M. (2024) · Multicriteria Algorithms with Applications · doi:10.61356/j.mawa.2024.4353 · Cited by 3
A Survey on Deep Learning-Based Traffic Signal Control
Qinbatu, S., Yang, L., Bao, J., Lin, Y., Bao, W., & Wu, C. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625300016 · Cited by 3
A Replaceable Curiosity-Driven Candidate Agent Exploration Approach for Task-Oriented Dialog Policy Learning
Niu, X., Ito, A., & Nose, T. (2024) · IEEE Access · doi:10.1109/access.2024.3462719 · Cited by 3
“Besides, we suggest optimizing dialog strategy in terms of action exploration, sampling all feasible actions as evenly as possible in the early training stage to avoid the agent consuming too much attention on individual actions [7].”
BackgroundMethodInfluential
Facilitating Robot Learning in Virtual Environments: A Deep Reinforcement Learning Framework
Laukaitis, A., Šareiko, A., & Mažeika, D. (2025) · Applied Sciences · doi:10.3390/app15095016 · Cited by 4
UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender SystemsPreprint
Liu, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4802791 · Cited by 3
Adinkra Symbol Recognition Using Classical Machine Learning and Deep LearningPreprint
Asamoah, K. O., Adjeisah, M., Yeboah, M. A., Raji, R. K., Achaab, G. F., & Adjei, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4836682 · Cited by 4
GACNet: Interactive Prediction of Surrounding Vehicles Behavior under High Collision Risk
Chai, J., Liu, J., Huang, J., & Huang, C. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202401040 · Cited by 2
NeuRL: A Standalone No-Code Web-Based Agent Environment to Explore Neural Networks and Reinforcement Learning
Siegel, S., Kapoor, A., & Rashidi, P. (2025) · ACM Technical Symposium on Computer Science Education (SIGCSE) · doi:10.1145/3641554.3701850 · Cited by 2
“In RL, models act as agents within an environment [3, 20].”
A deep reinforcement learning control framework for a partially observable system: experimental validation on a rotary flexible link system
Kumar, V. J., & Elumalai, V. K. (2025) · International Journal of Systems Science · doi:10.1080/00207721.2025.2468870 · Cited by 2
“For the exploration of action performed by the agents in the aforementioned RL schemes, several effective approaches including exploration policy and noisynet have been investigated in the literature (Ciosek et al., 2019; Fortunato et al.,2017 ; Ladosz et al., 2022).”
RL-DAUNCE: Reinforcement learning-driven data assimilation with uncertainty-aware constrained ensembles
Behnoudfar, P., & Chen, N. (2026) · Journal of Computational Physics · doi:10.1016/j.jcp.2026.115035 · Cited by 2
Reliability Evaluation for WSNs Based on Deep Reinforcement Learning and Graph Neural Networks
Xiao, Z., Liu, S., Lu, H., Yi, L., Gao, H., Deng, X., Wang, H., & Park, J. H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3595199 · Cited by 2
“In our architecture, the DRL agent interacts with the environment deﬁned by the network [34], and each component of the MDP is instantiated as follows: 1) Intelligent agent : In the AC algorithm, the intelligent agent consists of two networks, one is the actor network and the other is the critic…”
Regional Ecological Environment Quality Prediction Based on Multi-Model Fusion
Song, Y., Li, Z., & Wei, B. (2025) · Land · doi:10.3390/land14071486 · Cited by 2
A Dynamic Health Index Construction Framework Based on Deep Reinforcement Learning for Prognostic Analysis
Zhang, M., Sun, Y., Cao, Y., & Wang, F. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3597622 · Cited by 2
Learngene: Inheritable “genes” in intelligent agents
Feng, F., Wang, J., Yang, X., & Geng, X. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2025.104421 · Cited by 3
Enhanced exploration in reinforcement learning using graph neural network based intrinsic reward mechanism
Pandian, J. A., Thirunavukarasu, R., & Nagarajan, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-23769-3 · Cited by 2
Edge intelligence for space-air-ground integrated network: Challenges, solutions, and future directions
Chen, H., Qu, Y., Wu, T., ZHENG, J., Dong, C., & Wu, Q. (2025) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2025.103969 · Cited by 2
Fatigue inspection planning of offshore wind turbines: Deep reinforcement learning with information-directed exploration
Cheng, J., Zhang, F., Li, W., & Liu, Y. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.123954 · Cited by 2
Deep reinforcement learning framework for the underground mine short-term production scheduling problem
Li, N., Ding, Y., Dai, B., Wang, L., Chang, J., Ye, H., & Wang, Q. (2025) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2025.102229 · Cited by 2
Pursuit-evasion game of unmanned tracked vehicles based on multi-agent twin delayed deep deterministic policy gradient
Yao, J., Li, X., Zhang, Y., Chen, K., Li, Y., & Ji, J. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.113760 · Cited by 2
An evolutionary reinforcement learning framework for joint work package sizing and scheduling with uncertainties
Zhang, N., Li, X., & Xu, Z. (2026) · European Journal of Operational Research · doi:10.1016/j.ejor.2026.01.023 · Cited by 2
Air combat joint strategy learning based on a dual-loop framework and hindsight experience replay
Zhang, Y., Yang, Z., Zhang, B., Wang, X., Piao, H., & Zhou, D. (2026) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwag006 · Cited by 2
Expert-guided and action-compensated deep reinforcement learning for robust multi-ship collision avoidance in dynamic and uncertain maritime environments
Yu, S., Li, Y., & Gong, J. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.124354 · Cited by 2
Dynamic Fusion of Hyperspectral and LiDAR Data for Target Detection
Zang, X., Xu, L., Zhang, Y., Dong, Y., Shi, Q., Fang, L., & Du, B. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3661274 · Cited by 2
“DRL has been applied in various ﬁelds such as robotics, autonomous driving, and remote sensing [49].”
CMA-MAPPO: Integrating Covariance Matrix Adaptation Evolution Strategy with Multi-Agent Proximal Policy Optimization for enhanced exploration in sparse-reward environments
Khatami, A. H. (2026) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2026.102330 · Cited by 2
An End-to-End Learning Model With Quantization Technology for Dynamic Prediction-Decision Joint-Making in Active Distribution Networks
Cai, F., Dong, Z., Yang, X., Li, J., Hao, Z., He, Y., & Li, H. (2026) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2026.3668484 · Cited by 2
“With recent advances in deep reinforcement learning [17], [18], [19], [20], DRL-based voltage regulation and dispatch have demonstrated strong adaptability to uncertainty and dynamics [21], [22], [23].”
Meta reinforcement learning method for dynamic mission scheduling of earth observation satellites
Yao, W., Shen, X., Guo Zhang, A., Lu, Z., Wang, J., Gao, G., & Da, F. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112094 · Cited by 2
A Rule-Guided Distributional Soft Actor–Critic Algorithm for Safe Lane-Changing in Complex Driving Scenarios
Cui, S., Li, H., Su, Y., Huang, J., Cheng, K., & Li, H. (2026) · Vehicles · doi:10.3390/vehicles8030058 · Cited by 2
Data-driven prediction of oil spill risk in ship-to-ship bunkering by reinforcement learning and Bayesian belief networks
Türkoğlu, M. M., Cinar, F., & Akyüz, E. (2026) · Marine Pollution Bulletin · doi:10.1016/j.marpolbul.2026.119698 · Cited by 4
Reinforcement learning-based control co-design of digital twin-enabled full-vehicle active suspension systems
Tsai, Y.-K., Chen, Y.-P., Karkaria, V. N., & Chen, W. (2026) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-026-04304-y · Cited by 5
“For broader overviews of the DRL landscape, readers may consult comprehensive surveys in Arulkumaran et al. (2017); Ladosz et al. (2022); Wang et al. (2022).”
Leveraging big data-driven dynamic capabilities for enhanced decision making: a moderated-mediation approach
Altaf, S., Shafique, I., Qammar, A., Waqas, M., & Tariq, A. (2026) · Journal of Business Analytics · doi:10.1080/2573234x.2026.2658508 · Cited by 2
Review of synergy between machine learning and first principles models for asset integrity management
Cai, T., Fang, J., Daida, S., & Lou, H. H. (2023) · Frontiers in Chemical Engineering · doi:10.3389/fceng.2023.1138283 · Cited by 2
Integration of online deep reinforcement learning and federated learning: A dynamic energy management strategy for industrial applications
Tang, Y., Du, G., Long, J., & Zhao, Y. (2023) · IET Communications · doi:10.1049/cmu2.12686 · Cited by 2
Enhancing Value Estimation Policies by Post-Hoc Symmetry Exploitation in Motion Planning Tasks
Hasan, Y., Villegas-Suarez, A. M., Carter, E. C., Faust, A., & Tapia, L. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341746 · Cited by 2
“To address this issue, some methods rely on probabilistic sampling [5] to generalize for the symmetry, and other methods address it directly through experience augmentation [6] or latent space planning [7].”
Method
Bullet-Screen-Emoji Attack With Temporal Difference Noise for Video Action Recognition
Zhang, Y., Zhang, H., Li, J., Shi, Z., Yang, J., Yang, K., Yin, S., Liang, Q., & Liu, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3455799 · Cited by 2
“Reinforcement learning has been successfully applied to a variety of computer vision tasks [40], [41], [42], [43], [44], [45], [46].”
Reinforcement Learning-Based Network Dismantling by Targeting Maximum-Degree Nodes in the Giant Connected Component
Liu, S., Pu, T., Zeng, L., Wang, Y., Cheng, H., & Liu, Z. (2024) · Mathematics · doi:10.3390/math12172766 · Cited by 2
Sensor management method based on TD3 in multi-target tracking
Zhang, X., Chen, H., & Zhang, W. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad96d3 · Cited by 2
“…advancement of artificial intelligence technology has driven a profound transformation in intelligent decision-making techniques, particularly deep reinforcement learning (DRL) [25, 26], which has attracted considerable attention and has started to be applied in various sensor management tasks.”
Model-free adjustment of reducing agent for SCR device under label deficiency: Regulation-oriented stage-wise reward deep Q-learning with transfer-learned state
Jiang, H., Zhang, S., Liu, J., Peng, X., & Zhong, W. (2025) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2024.12.126 · Cited by 2
Reinforcement Learning in Mechatronic Systems: A Case Study on DC Motor Control
Nüßgen, A., Lerch, A., Degen, R., Irmer, M., de Fries, M., Richter, F., Boström, C., & Ruschitzka, M. (2025) · Circuits and Systems · doi:10.4236/cs.2025.161001 · Cited by 2
“The application of DoE enables the RL agent to be trained in a manner that ensures consistent control performance under varying conditions, thereby enhancing its flexibility in more complex environments [8] [9].”
DRLLog: Deep Reinforcement Learning for Online Log Anomaly Detection
Zhou, J., Gao, Y., Ying, Z., Yu, X., Yang, Y., Tan, C., & Xiang, J. (2025) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2025.3542595 · Cited by 2
“DRL uses a method that combines deep neural networks and reinforcement learning to interact between the agent and the environment and achieve the goal by learning the optimal strategy [18].”
Integrating FedDRL for Efficient Vehicular Communication in Smart Cities
Mancini, L., Labbi, S., Abed‐Meraim, K., Boukhalfa, F., Durmus, A., Mangold, P., & Moulines, É. (2025) · Lecture notes in intelligent transportation and infrastructure · doi:10.1007/978-3-031-72959-1_19 · Cited by 2
Overcoming intermittent instability in reinforcement learning via gradient norm preservation
Park, J., Lee, J., Kim, J., & Han, S. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122081 · Cited by 2
An adaptive pairwise testing algorithm based on deep reinforcement learning
Wen, L., Mao, C., Towey, D., & Chen, J. (2025) · Science of Computer Programming · doi:10.1016/j.scico.2025.103353 · Cited by 2
Learning generalizable agents via self-supervised exploration
Liang, B., Xu, L., & Deng, Z. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107787 · Cited by 2
Multimodal Data Fusion and Adaptive Optimization in Tennis Training Based on Deep Deterministic Policy Gradient and IoT Sensors
Yang, Z. (2025) · Informatica · doi:10.31449/inf.v49i25.8485 · Cited by 2
Human-Like Bots for Tactical Shooters Using Compute-Efficient Sensors
Justesen, N., Kaselimi, M., Snodgrass, S., Vozaru, M., Schlegel, M., Wingren, J., Barros, G. A. B., Mahlmann, T., Sudhakaran, S., Kerr, W., et al. (2025) · IEEE Transactions on Games · doi:10.1109/tg.2025.3593919 · Cited by 2
“For instance, issues related to model stability and the limited exploration [9] present in the demonstrated behaviors of experts are some of the challenges that modern imitation learning algorithms face in that domain.”
(Ir)rationality in AI: state of the art, research challenges and open questions
Macmillan-Scott, O., & Musolesi, M. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11341-4 · Cited by 12
“Ladosz et al. (2022) consider three approaches to address this inefficiency: reduced states/actions for exploration methods, exploration parameters methods, and network parameter noise methods.”
Free Energy Projective Simulation (FEPS): Active inference with interpretability
Pazem, J., Krumm, M., Vining, A. Q., Fiderer, L. J., & Briegel, H. J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331047 · Cited by 4
“RL with internal rewards: Finding efficient exploration strategies constitutes an essential problem in RL [41].”
Hardening Active Directory Graphs via Evolutionary Diversity Optimization-based Policies
Goel, D., Ward, M., Neumann, A., Neumann, F., Nguyen, H., & Guo, M. (2024) · ACM Transactions on Evolutionary Learning and Optimization · doi:10.1145/3688401 · Cited by 2
“Section 10 presents the discussion, and Section 11 concludes the paper.”
Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
Qian, Y., Yu, P., Wu, Y., Su, Y., Wang, W., & Fan, L. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802420 · Cited by 2
“Reinforcement-learning-based models can perform goal-conditioned decisions, but could suffer from sparse reward, low data efficiency [11], and low environment and task generalization ability [12].”
Adaptive algorithms for shaping behavior
Tong, W. L., Iyer, A., Murthy, V. N., & Reddy, G. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013454 · Cited by 2
“However, these approaches rely on arbitrary control over the agent’s states [22–24], exploration [25–32] or the reward structure [33–35].”
Balancing a Cart Pole Using Reinforcement Learning in OpenAI Gym EnvironmentPreprint
Mishra, S., & Arora, A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768234 · Cited by 2
Merits of curiosity: a simulation studyPreprint
Gruaz, L., Modirshanechi, A., Becker, S., & Brea, J. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/evm9n · Cited by 2
To Exit or Not to Exit: Cost-Effective Early-Exit Architecture Based on Markov Decision Process
Kim, K., & Lee, H.-S. (2024) · Mathematics · doi:10.3390/math12142263 · Cited by 1
A Motion Planner Based on Mask-D3QN of Quadruped Robot Motion for Steam Generator
Xu, B., Zhang, X., Yu, X., Ou, Y., Zhang, K., Cai, H., Zhao, J., & Fan, J. (2024) · Biomimetics · doi:10.3390/biomimetics9100592 · Cited by 1
Fluid identification in geological exploration using transformer models and deep reinforcement learning
Yin, W., Li, H., Zhao, Z., & Qiao, S. (2025) · Physics of Fluids · doi:10.1063/5.0248592 · Cited by 1
Multi-agent Deep Reinforcement Learning for Coverage in Unknown Environments
Sanghvi, N., Niyogi, R., & Yadav, O. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-87778-0_9 · Cited by 1
Combining meta reinforcement learning with neural plasticity mechanisms for improved AI performance
Liu, L., & Xu, Z. (2025) · PLoS ONE · doi:10.1371/journal.pone.0320777 · Cited by 1
“Reinforcement Learning (RL) serves as a cornerstone in AI, specifically in teaching machines to learn from their environment and make strategic decisions [16–23].”
Double Deep Q-Learning Network for Package Pickup and Delivery Route Prediction
Gubena, M. M., Zhang, Y., Ma, Z., Ma, X., & Yang, Y. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3577902 · Cited by 1

Authors: Ladosz, P., Weng, L., Kim, M., & Oh, H.
Affiliations: OpenAI (United States) (US)
Ulsan National Institute of Science and Technology (KR)
Corresponding author: Oh, Hyondong
ORCID: Kim, Minwoo
Oh, Hyondong
Venue: Information Fusion
Publisher: Elsevier BV
Published: 2022-09
Volume: 85
Pages: 1-22
ISSN: 1566-2535 (ISSN-L)
DOI: 10.1016/j.inffus.2022.03.003
OpenAlex: W4220747123
Cited by: 525
References: 185
Citations by year: 2026: 112 · 2025: 198 · 2024: 149 · 2023: 59 · 2022: 7
FWCI: 33.97
Type: journal article
Language: en
Open access: green
arxiv.org
Licence: www.elsevier.com/tdm/userlicense/1.0/ (tdm)
www.elsevier.com/legal/tdmrep-license (tdm)
doi.org/10.15223/policy-017 (stm-asf)
doi.org/10.15223/policy-037 (stm-asf)
doi.org/10.15223/policy-012 (stm-asf)
doi.org/10.15223/policy-029 (stm-asf)
doi.org/10.15223/policy-004 (stm-asf)
Locations: Information Fusion (publishedVersion)
arXiv (Cornell University) (submittedVersion)
Research Explorer (The University of Manchester) (submittedVersion, cc-by-nc-nd)
Scholarworks@UNIST (Ulsan National Institute of Science and Technology) (submittedVersion)
arXiv (Cornell University)
Funders: Ministry of Science, ICT and Future Planning (2020M3C1C1A01082375, 2020R1F1A1049066)
National Research Foundation of Korea
Ministry of Education (2020R1A6A1A03040570)
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
Keywords: safe exploration, random exploration, reward learning

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

Exploration in deep reinforcement learning: A survey

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks