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 accessOverview
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
Cites
Statistics
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Solving these problems requires a good global exploration strategy [211] that can better balance long-term and short-term environment information [195].”
From Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects (2023) · cites this paper as [195]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“While underappreciated in current reasoning literature, the exploration component of RL has long been recognized as a critical driver for emergent behavior in traditional RL (Yue et al., 2025; Silver et al., 2016; Ladosz et al., 2022; Pourcel et al., 2024).”
From Absolute Zero: Reinforced Self-play Reasoning with Zero Data (2025) · cites this paper as Ladosz et al., 2022
In the citing paper
“This subdomain is dedicated to developing AI systems capable of smooth, natural, and context-aware human-computer interactions, by focusing on dialogue modeling, question answering, user intent recognition, and multi-turn context tracking [204], [205], [206], [207].”
From From Google Gemini to OpenAI Q* (Q-Star): A Survey on Reshaping the Generative Artificial Intelligence (AI) Research Landscape (2025) · cites this paper as [206]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
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].”
BackgroundReinforcement 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].”
MethodLabaca-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].”
BackgroundSimple 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].”
BackgroundProceedings. 1985 IEEE International Conference on Robotics and Automation
(1985) · doi:10.1109/robot.1985 · Cited by 3,692
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.
Cited by
Sorted by citations
Items 401–500 of 528
From LLMs to Randomness: Analyzing Program Input Efficacy With Resource and Language Metrics
Black, G., Yocam, E., Vaidyan, V. M., Comert, G., & Wang, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3571205
“Fuzzing techniques can be greatly enhanced by using machine learning, especially reinforcement learning and transformer-based architectures [20], [21].”
Optimality Analysis of Reinforcement Learning-based Reactive Power Control
Bi, C., Xu, H., Fu, C., Zhang, X., Zhu, S., & Li, S. (2025) · International Conference on Smart Grid and Artificial Intelligence (SGAI) · doi:10.1109/sgai64825.2025.11009393
“…learning (RL) offers a promising alternative as a self-supervised machine learning approach that does not depend on explicit system model parameters, Instead, RL learns optimal strategies through iterative interactions with the environment, effectively addressing the curse of dimensionality [6].”
A deep reinforcement learning framework for optimized dummy pad placement in PCB electroplating
Zhou, Q., Li, Y., Wang, C., & Wang, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128639
Hou, Z., Li, C., Liu, P., Li, X., Liu, Y., & Jin, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9914-8_10
Amarat, S. B., Shi, C., & Wang, Y. (2025) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd64986.2025.11082009
Liang, X., Liu, S., Wang, H., Zhang, Q., & Zhao, B. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0009-3_38
Yuan, W., He, H., Hou, Y., Chen, S., Jiang, X., & Yang, J. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3725945
Yuan, T., Liu, Z., Fang, Y., & Deng, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9894-3_10
Construction of deep space communication channel environment prediction model based on deep learning
Bian, K. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-11557-z
“There are also studies that try to use reinforcement learning [28, 29] or generative adversarial networks (GAN) [30, 31] to optimize resource allocation and channel prediction in deep-space communication systems.”
Deep reinforcement learning-based composite path planning with key path points
Sun, C., Wang, J., Mu, C., Liangping, X. I. N. G., & Changyin, S. U. N. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0101
Boosting Exploration in Reinforcement Learning for Sparse Reward Tasks
Zhang, Y., Lyu, Y., Zhan, G., Zou, W., & Li, S. E. (2025) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc63710.2025.11107911
“This preference presents significant challenges for existing RL algorithms to achieve satisfactory performance, especially when confronted with sparse reward tasks [4], [5].”
Custom Environment Navigation System Using Reinforcement Learning
Singhal, A., Kaur, K., Bharti, S., Lodhi, E. A., & Kumar, A. (2025) · International Conference on Computing Technologies (ICOCT) · doi:10.1109/icoct64433.2025.11118394
Maisonneuve, L., & Lehmann, L. (2026) · Evolutionary Human Sciences · doi:10.1017/ehs.2026.10044
Yi, Z., Li, W., & Dai, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5440544
A proposed DDPG-RL-Agent strategy for MRD vibration controlPreprint
Huang, W., & Xu, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5439841
Weakly supervised multi-modal imitation learning from incompletely labeled demonstrations
Gu, S., & Zhu, F. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108098
Evaluating the Impact of Data Curation on Off-Policy Reinforcement Learning
Blum, M., & Eivazi, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04558-4_28
Wang, S., Zhou, Z., & Wang, Z. (2025) · Conference on Fully Actuated System Theory and Applications (FASTA) · doi:10.1109/fasta65681.2025.11139049
“The combination of deep learning and reinforcement learning is referred to as deep reinforcement learning (DRL)[6].”
Xiang, R., Pengwei, M. A., Gong, L. J., Tian, M., Li, R., Fei, H., & Yi, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5460095
Ma, L. (2025) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns-2025-1041
Fundamentals of machine learning
Mustafa, K., Rezakazemi, M., & Mahboob, R. M. M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-27422-0.00010-4
A teacher-student reinforcement learning framework for temperature control in solar greenhouses
Yu, J., Wei, X., Munnaf, M. A., Ma, L., Peng, S., & Sun, C. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101498
MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Model
Chen, Y., Habchi, S., & Wei, L. (2025) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1109/ase63991.2025.00012 · Cited by 4
“Furthermore, RL tools often depend on developer-defined rewards [76], introducing expert bias, whereas IL tools rely heavily on human demonstrations, limiting flexibility.”
A Hybrid Reinforcement Learning Approach for Cargo Delivery by Autonomous Drone
Karaköse, E., & Bayraktar, B. (2025) · Firat University Journal of Experimental and Computational Engineering · doi:10.62520/fujece.1652790
Dissociation between temporal and spatial variability in locomotor development
Wang, J., Bulu, E. S., Khater, S. A., & Seethapathi, N. (2025) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/icdl63968.2025.11204398
“A salient characteristic of RL is random exploration, Technology, Cambridge, MA, USA nidhise@mit.edu which often manifests behaviorally as unstructured variability along many possible dimensions of action [2].”
Bao, Y., Zhang, J., Yi, C. X., Zhang, D., & Fu, R. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02106-1
“Deep reinforcement learning (DRL) [46, 47], which has achieved excellent performance in solving complex decision-making problems in recent years [25], becomes our first choice.”
Multimodal Dual Population Evolutionary Reinforcement Learning
Zhang, Y., Huang, P. S., & Zhang, R. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755206
“Reinforcement Learning (RL) continuously optimizes policies via agent-environment interaction [24], demonstrating exceptional performance in domains such as robotic control and game intelligence [1, 25].”
Reward Contrast Method for Reinforcement Learning Exploration
Roland, C., & Kim, J.-D. (2025) · International Conference on Mobile Computing and Ubiquitous Network (ICMU) · doi:10.23919/icmu65253.2025.11219110
“Ladsoz et. al [4] classify various methods in two groups: efficiency methods which is subsequently divided in more sub-groups and safe exploration.”
Chen, Y., Yan, H., & Ding, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113069
Active Suspension Performance Enhancement Based on Improved DDPG Algorithms
Cao, S., Gao, X., Zhang, G., Han, S., & Du, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227947
“Through interaction with the environment, RL continuously learns how to make optimal decisions [1] in complex and ever-changing environments to maximize the achievement of goals.”
Improving RL Exploration for LLM Reasoning Through Retrospective Replay
Dou, S., Wu, M., Xu, J., Zheng, R., Gui, T., & Zhang, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3343-5_46
Integrating Exploration into Case-Based Reasoning: A Strategy for Enhanced Knowledge Acquisition
Boulmaiz, F., Reignier, P., & Ploix, S. (2025) · Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing · doi:10.1109/snpd65828.2025.11253279
“This can lead to slower convergence toward viable solutions and higher computational expenses due to the absence of targeted exploration [7].”
Distributed Privacy-Preserving Reinforcement Learning via Sparse Matrix Encryption for IoT
Ji, T., Liang, Y., Tao, Y., Kong, F., Ge, C., Qin, B., & Yu, J. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3638777
“To balance these two, the (cid:15) -greedy strategy is commonly used [27].”
Xing, Y., Ding, X. D., & Ding, X. (2025) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon67449.2025.11267754
“…agents can iteratively improve their action-value estimates in discrete state spaces, while advances such as Deep Q-Networks (DQN) and actor-critic methods extended these capabilities to high-dimensional, continuous settings by leveraging deep neural networks for function approximation [9], [10].”
Wong, P. K., Wang, X., & Thalagala, S. (2025) · International Journal of Automotive Technology · doi:10.1007/s12239-025-00385-8
“With the rapid development of artificial intelligence, reinforcement learning (RL) has emerged as a promising control approach (Ladosz et al., 2022; Matsuo et al., 2022; Zhao et al., 2023).”
Deep Reinforcement Learning for Robotic Navigation: A Study on the Role of Epsilon-Greedy
Furlaneto, F. P., Santos, M. V., Becker, M., Caurin, G. A. P., Vivaldini, K. C. T., & Joaquim, R. C. (2025) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars69345.2025.11272966
“Recent studies [10] show that the ϵ decay rate significantly influences the convergence time, but its sensitivity in simultaneous mapping scenarios, where geometric uncertainty is critical, is still poorly explored.”
From Sparse to Dense: Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning
Park, J., Yang, H., Lee, M. W., Choi, W.-S., Lee, M., & Zhang, B. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3642038 · Cited by 4
“Balancing exploration and exploitation is a cornerstone challenge in deep RL [19].”
Enhancing Distributed System Performance with an Intelligent Multi-Agent Microservices Architecture
Zouad, S., & Boufaïda, M. (2025) · International Journal of Interactive Mobile Technologies (iJIM) · doi:10.3991/ijim.v19i24.56299
Shaping Q -values right: A distributional normalized actor–critic approach
Park, J., Kim, J., & Han, S. H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112779
Li, F., Dong, Y., Du, X., Jin, J., Tong, N., Xu, F., & Wang, D. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228724
“Deep reinforcement learning combines the environmental awareness of deep learning with the decision-making ability of reinforcement learning [15].”
Reinforcement Learning to Reduce Papr in Communication Systems
da Silva, B. S. D. C., Pereira, L. A. M., & Mendes, L. L. (2025) · Workshop on Communication Networks and Power Systems (WCNPS) · doi:10.1109/wcnps69127.2025.11295904
“Deep Deterministic Policy Gradient (DDPG) [19] is an algorithm that also deals with continuous states and actions.”
Multi-Agent Reinforcement Learning for Hybrid Impulsive Formation Tracking
Gu, Y., & Zhen, S. (2025) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus66297.2025.11294082
“Based on trial-and-error learning, the agent iteratively refines its policy with the objective of optimizing long-term accumulated rewards [10].”
Xiang, R., Pengwei, M. A., Gong, L., Tian, M., Li, R., Fei, H., & Yi, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5967994
Zheng, L., Ni, J., Zobel, C. W., & Birge, J. R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5991354
Hyper-Dimensional Computing Powered DRL for Task Offloading in Edge-Enabled Consumer Electronics
Zhao, X., He, X., Xu, X., & Alsolai, H. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3656226
“This issue is critical because it directly affects the performance and stability of the algorithm [43], [44].”
Research on Financial Trading Algorithms Based on Deep Reinforcement Learning
Guo, X. (2025) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect64621.2025.11339735
“…spaces, traditional tabular Q-learning may face the problem of dimensional catastrophe, which has prompted the emergence of improved methods incorporating deep learning such as deep Q-networks (DQNs), which further extends the potential of Q-learning for applications in complex environments [6].”
Pirinsky, C. A. (2026) · Springer eBooks · doi:10.1007/978-3-032-13334-2_3
DSAC-ICM: A Distributional Reinforcement Learning Framework for Path Planning in 3D Uneven Terrains
Zhou, Y., Liu, F., Liu, Z., Ji, X., & Yin, G. (2026) · Sensors · doi:10.3390/s26030853
“Additionally, sparse and delayed goal-reaching rewards limit exploration, causing the agent to get stuck in local minima and fail to find traversable routes [18].”
Παναγόπουλος, Δ., Perrusquía, A., & Guo, W. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342671
“…exploration, whether ε -greedy, Boltzmann, or even maximum-entropy variants, often assume a stationary environment with fixed priorities, failing to account for the fluid nature of SAR missions where the relative importance of information types can shift abruptly as the situation evolves [1], [2].”
Adaptive Exploration in Deep Reinforcement Learning via Uncertainty-Aware State Representation
Kolla, T., Babu, T., & Nair, R. R. (2025) · International Conference on Advancements in Computing (ICAC) · doi:10.1109/icac69156.2025.11361472
“Ladosz et al. have done an extensive study [10] on intrinsic motivation and curiosity-driven learning as other types of exploration mechanisms as well as ensemble-based exploration mechanisms.”
Wang, H., Wang, Z., Yang, L., & Shi, H. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115540
EPRS: Experience-Prioritized Reinforcement Scheduler in Edge Clusters
Tan, S., Huang, T., Zhu, E., Qin, J., & Fan, X. (2026) · Sensors · doi:10.3390/s26041168
Wang, S. Y., Zhang, Q., Pan, R., Li, Y., Wu, C., Che, W. Q., Xue, Q., Kang, K., & Li, Y. (2026) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2026.3661765
“RL provides a natural solution by enabling iterative interaction with simulators and incorporating multiple objectives into reward functions [29].”
Zhenhao, J. I. A. O., Xiaogang, C. H. E. N., Tao, H. O. N. G., Li, S., Xi, L. I., Chengcai, T. U., Dai, W., & Zhitang, S. O. N. G. (2026) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2025eal2096
Zhu, A., Yang, Y. Y. Y., Zhao, G., & Shao, J. (2026) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70109
Hsu, H.-C., Lin, Y.-H., Chen, Y., & Wang, Y.-J. (2025) · International Conference on Automation Technology (Automation) · doi:10.1109/automation66991.2025.11389893
“Such sparse reward slows exploration and may produce control trajectories without minimizing state errors [3], [4].”
Zheng, S., Gao, Y., Liu, A., Li, W., Chen, T., & Yin, H. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3666242
“The sparsity of links in TKGs is positively correlated with the sparsity of the action selection in multi-hop reasoning methods [29], [30].”
Li, X., Zhang, Q., Jia, Q., Cheng, J., & Wang, X. R. (2025) · International Conference on Cyber-Energy Systems and Intelligent Energy (ICCSIE) · doi:10.1109/iccsie67394.2025.11377570
“To address SCOPF’s slow convergence under multiple faults, [18] used parallel computing with coarse task partitioning, improving efficiency but still facing high complexity, parameter dependence, and large simulation demands, which hinder real-time use.”
Exploiting LiDAR Symmetries to Enhance Value Estimation Policies
Hasan, Y., Faust, A. B., Carter, E. C., & Tapia, L. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3668446
“The method is compared with the baseline policy, as well as an abstraction based method [24] and an extended training time method [25].”
CVAE-GAN-Driven Latent State Similarity for Sparse-Reward Deep Reinforcement Learning
Cao, J., Hu, J., Huang, L., Guo, P., Tan, S., & Wu, J. (2025) · International Conference on the Frontiers of Electronic, Electrical and Information Engineering (ICFEEIE) · doi:10.1109/icfeeie66944.2025.00011
“…investigation into lightweight architectures and federated learning paradigms; and (3) Safety-critical strategy risks induced by intrinsic reward mechanisms (e.g., catastrophic collision avoidance failures in autonomous driving scenarios), mandating development of safety-constrained RL [11][12].”
Chen, X., Li, B., Chen, B., Sun, H., Dong, L., Yin, G., & Weichao, Z. (2026) · Electronics · doi:10.3390/electronics15061178
A Reinforcement Learning Framework for Autonomous Behavior Tree Construction in Door Traversal Tasks
Paoamnartrit, H., Thamrongaphichartkul, K., Sakulkueakulsuk, B., & Vongbunyong, S. (2025) · International Conference on Robotics, Automation and Artificial Intelligence (RAAI) · doi:10.1109/raai67517.2025.11423416
“Techniques to address this problem include curriculum learning [8], reward shaping, and exploration strategies [9].”
Yan, M. G., Guo, H., Xiong, R., Chan, C. A., Gygax, A. F., & Wong, E. (2025) · Globecom · doi:10.1109/globecom59602.2025.11432146
“Agents in a DRL network can choose the optimal action according to the current network environment state and adjust the strategy according to the network environment feedback; this enables the determination of the optimal resource allocation strategy under limited conditions [8].”
Jia, C., & Yu, T. (2026) · Journal of Control Automation and Electrical Systems · doi:10.1007/s40313-026-01276-8
“Deep neural networks have been introduced to approximate policies and Q-functions, giving rise to deep reinforcement learning techniques (Ladosz et al., 2022).”
Learning to Grasp in Robotics with Quality-Diversity Generated Data
Huber, J. B. (2024) · theses.fr (ABES) · doi:10.70675/b98f392dz4df9z4646z8b34z59f447564543
Task Specification and Generalization in Multi-Task Reinforcement Learning
Cachet, T. (2025) · theses.fr (ABES) · doi:10.70675/08eadb30z8466z4763zbba6za6a4dab9a29e
On Learning-Based Control of Dynamical Systems
Boucher, R. H. (2025) · theses.fr (ABES) · doi:10.70675/67349913z9267z494ez8c88z8ed908b6a102
Predictive modeling for disease prevention
Goel, R., Mishra, R., Puri, D., Raj, G., & Singh, N. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44958-1.00018-5
Neuro-Fuzzy Enhanced Deep Reinforcement Learning for Adaptive Urban Traffic Signal ControlPreprint
Soroyewun, M. B., Obiniyi, A. A., Junaidu, S. B., & Adedokun, E. A. (2026) · Research Square · doi:10.21203/rs.3.rs-9396900/v1
Uncertainty-aware algorithmic trading in a teacher–student framework
Dong, L., Chen, L., Bing, Y., Zhang, H., Zhang, W., & Pan, R. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115294
Sang, H., Li, J., Ye, Y., & Wang, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-16794-1_10
KPI-Adaptive DQN Framework for Handover Optimization in 5G Ultra-Dense Networks
Munir, M. U., Ahmedy, I., Noor, R. M., Azzuhri, S. R., Sharmin, S., & Iqbal, U. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0306-2_14
A Novel Framework to Evaluate Generalization Performance of Deep Reinforcement Learning
Tian, Y., Wu, Q., & Chen, L. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487359
“…purpose, current research of RL mainly focuses on optimization problems, leading to a reward–centered evaluation framework that includes total, mean, and human normalized rewards [4] in deep Q–learning (DQN) algorithms [5], [6], actor–critic methods [7], [8], and other advanced approaches.”
Li, H., Tang, X., Lu, J., Wei, A., & Mao, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3688475
“MDP is a widely adopted framework for modeling environment-interactive decision-making systems [42].”
Reinforced Temporally Sparse Gating for High-Fidelity Speech Watermarking
Fang, X., Li, J., Liu, J., & Zou, L. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3690581
“This framework serves as the core of our reinforcement learning-based fine-tuning process [16], [17], [18].”
Deng, Y., Xu, C., Mo, W., & Wan, C. (2026) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2026.3690001
“The number of feasible link-related actions in the network is large, while most actions exert only marginal influence on system performance, resulting in sparse feedback signals [22].”
Mia-grl: mutual information aligned generative reinforcement learning with missing data
Ma, A., Li, P. Q., Chen, J., Su, X., & Chen, S. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02313-4
Yi, Z., Wu, Z., Xie, Y., Chen, M., & Dai, Y. (2026) · Mathematics · doi:10.3390/math14101624
A Hybrid Deep Learning Framework with Q-Table Optimization for Well Log Reconstruction
Yu, H., & Zhao, B. (2026) · Processes · doi:10.3390/pr14101548
Li, X.-Z., Hsu, H.-H., & Chao, W.-H. (2025) · International Conference on Education and E-Learning (ICEEL) · doi:10.1145/3789859.3789890
“Reinforcement learning agents often struggle in complex environments due to sparse rewards and high penalties, which reduce sample efficiency and destabilize learning [4].”
Xu, K., Wang, Z., Zhao, Y., & Fang, B. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109110
Chu, C., Zhang, J., Zhang, Y., He, P., Chen, Y., Liu, Q., & Chen, Y. (2026) · Physical Communication · doi:10.1016/j.phycom.2026.103177
Condition-aware deep reinforcement learning for optimization of a microchannel heat sink
Hassanzadeh, M., Ebrahimi, M. Y., Sayyah, M., & Shamloo, A. (2026) · International Communications in Heat and Mass Transfer · doi:10.1016/j.icheatmasstransfer.2026.111521
Li, D., Wang, Y., Chen, Z., Ren, X., & Tao, T. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-6817-8_1
Qu, Z., & Wang, Q. (2026) · Scientific Reports · doi:10.1038/s41598-026-55002-0
Song, Y., Guo, Y., Xing, L., Wu, J. D., Wang, J., Huai, S., & Pedrycz, W. (2026) · Advances in Space Research · doi:10.1016/j.asr.2026.06.023
Temporal difference learning with constrained initial representations
Lyu, J., Yang, J., Qiao, Z., Liu, R., Liu, Z., Ye, D., Lu, Z., & Li, X. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123774
Pan, Z., Chen, C., Liu, Y., & Zheng, H. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115436
Yin, X., Yang, H., Wu, W., & Wang, W. Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134291
Noise-based reward-modulated learning
Fernández, J. G., Ahmad, N., & van Gerven, M. A. J. (2026) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ae7ea7 · Cited by 1
“This proves that higher sample sizes reduce the gradient approximation error without requiring a clean pass.”
Enhanced Prediction of Gut Microbiome–Related Diseases Using Hybrid Machine Learning ModelsPreprint
Marisetti, S. A., Chatterjee, P., & Priyakumar, U. D. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.24.734177
Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning
Wang, A., Lei, M., Zhang, H., Gao, Z., Zhang, Q., Zhang, Z., Zhu, P., Deng, D., Zu, L., Yang, G., et al. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3707748
“Although uncertainty-aware exploration can in principle guide policies toward epistemically uncertain regions [13], its use in medical planning remains limited.”
Effective Exploration via Intrinsic Motivation in Reinforcement Learning
Eren, B., & Demіr, A. (2026) · Journal of Advanced Research in Natural and Applied Sciences · doi:10.28979/jarnas.1922504
A GA-RL Hybrid Framework for E-Paper Waveform Optimization
Mo, Z., Zhuo, H. H., & Zhou, Z. (2026) · International Conference on Machine Intelligence Theory and Applications (MiTA) · doi:10.1109/mita69365.2026.11582419
“RL , in contrast, employs an agent that learns optimal adjustment strategies through iterative interaction with the E-paper system, using color difference as a reward signal [9].”
Zhang, C., Gui, X., Li, B., Chen, J., Jie, B., & Zhang, Y. (2026) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2026.3710705
Robust Quadruped Locomotion via Evolutionary Reinforcement Learning
McAteer, B., & Mason, K. (2026) · International Conference on Control and Robotics Engineering (ICCRE) · doi:10.1109/iccre69951.2026.11593505
“When combined with deep neural networks, known as Deep Reinforcement Learning (DRL), these systems have demonstrated remarkable capability across domains involving high-dimensional sensory input and continuous control [5].”
Shuklana, B., Rani, S., & Saini, C. (2026) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/ic2pct68894.2026.11584388
“This paper present a theoretically motivated and novel fusion of these two complementary model inspired by the fundamental but key concepts by Late Sir David Mackay in his books he address key insights on information theory [10]especially for high dimensional environment.”
Huang, J., Xi, G., Lin, M., Zhang, H., Li, B., & Neretin, E. S. (2026) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70153
Chen, J., Teng, Q., Qu, L., Bu, S., & Mai, H. (2026) · Electric Power Systems Research · doi:10.1016/j.epsr.2026.113804
Wang, C., Wang, Z., Zhang, S., Xiang, Y., Li, Z., Li, L., & Tan, J. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101166
Metadata
- 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
- Venue
- Information Fusion
- Publisher
- Elsevier BV
- Published
- 2022-09
- Volume
- 85
- Pages
- 1-22
- ISSN
- 1566-2535 (ISSN-L)
- 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
- 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
