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 501–528 of 528
Emerging Paradigms in Artificial Intelligence: A Review for Management Perspective
Zakaria, A., Arof, A. M., & Din, M. A. (2026) · SpringerBriefs in applied sciences and technology · doi:10.1007/978-3-032-26565-4_14
RAISE: Reward-Aware Intrinsic Learning for Sparse Extrinsic Reward Reinforcement Learning
Yue, W., Zheng, J., Wang, Z., & Wang, L. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3381-6_38
Li, X., Jiang, J., Liu, W., Wang, X., & Liang, X. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3717171
“While distributional RL can improve the training stability and speed, it cannot deal with the problems of risky exploration and ine ffi cient sampling inherent in the online learning paradigm [29], [30].”
Ma, J., Zhang, Y., Ma, H., & Jin, Y. (2026) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda70336.2026.11621295
“…feasible actions [7], yet still explore all cells; this Supported by the National Natural Science Foundation of China (Grant No. 62473052) and the National Key Laboratory Program (Grant No. 241-HF-D09-01). is costly when exploration and evaluation protocols affect deep-RL results [8], [9].”
A Federated LLM-Based Framework for DDoS Defense in Mobile Edge Computing
Shuo, Z., Kousuke, M., & Toshio, H. (2026) · IEEE International Conference on Fog and Edge Computing (ICFEC) · doi:10.1109/icfec69006.2026.00017
“For LLama2 model, we utilize the Huggingface Autoto-kenizer [18] configured with the Byte-Pair Encoding (BPE) algorithm.”
Zhang, J., Zhang, L., Zhang, B., Wang, W., Liu, W., Yao, L., Cui, L., & Zhang, M. (2026) · Aerospace · doi:10.3390/aerospace13080692
“Some works model the laser engagement process by incorporating irradiation time and damage probability into the assignment objective [18,19].”
Hu, Y. (2026) · Autex Research Journal · doi:10.1515/aut-2025-0090
“By integrating causal graph modeling [26], disentangled representation learning, and e ff ective exploration strategies [27], DCDRL learns separate embeddings for intrinsic pro-environmental motivation and behavioral biases.”
Wang, C., Chen, X., Shen, A., & Yang, J. (2026) · Sensors · doi:10.3390/s26154882
“Although existing studies have confirmed the effectiveness of MARL in collaborative tasks, several critical issues remain that must be addressed urgently for its application in collaborative exploration of unknown environments [9,10].”
Q-FOX Learning: Breaking Tradition in Reinforcement Learning
Jumaah, M. A., Ali, Y. H., & Rashid, T. A. (2026) · Signals and communication technology · doi:10.1007/978-3-032-18834-2_28
Zhang, X., Wang, C., Liu, Y., Lv, T., & Zhang, J. (2026) · 2026 IEEE 3rd International Conference on Big Data Science and Engineering (ICBDSE) · doi:10.1109/icbdse70225.2026.11635245
Chang, Q., Gao, S., Zhou, Y., Ren, H., Su, R., Wu, W., & Chen, X. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116005
Reinforcement learning-based landing control of an asteroid-hopping rover
Train, T., Keshtkar, S., & Kojima, H. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.08.046
Reliable Task Allocation for Multirobot System Using Safe Deep Reinforcement Learning
Mu, C., Zhang, J., Wang, K., & Liu, D. (2026) · IEEE Transactions on Reliability · doi:10.1109/tr.2026.3727234
“Alternative optimization strategies employ low-order Taylor expansions to approximate nonconvex constraints, subsequently applying convex optimization techniques to solve dual variables [41].”
Flight-Timing Hierarchical Surrogate-Based Optimization for Sparse-Window UAV-IoT Packet Collection
Jiang, Y., & Yan, Q. (2026) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2026.3726926
“Evolutionary optimizers receive little selection pressure before rate-feasible schedules emerge, and sparse-reward deep reinforcement learning typically requires far more interaction [14] than the budget considered here.”
Gaussian processes with prior-model-informed kernel for dynamical system modeling
Tang, S., Xiao, C., He, B., & Li, N. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109569
Diverse Episodic Trajectory Exploration for Deep Q-Networks With Application to Self-Driving Cars
Hassani, H., Nikan, S., & Abdallah Shami, B. (2026) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2026.3732856
“Considering efficiency, exploration strategies typically fall into three categories including planning-based, intrinsic reward-based, and random-based [47].”
Towards Security and Efficient Cloud Resource Scheduling with Double Deep Q-Networks
He, M., Xiong, L., & Liu, Z. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-9514-3_15
Experiments on Multi-UAV Path Planning Using DRL Based on Graph Neural Networks
Fu, M., Chen, W., Zhuo, X., Chen, H., & Chen, F. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-92-3566-7_29
Kakavand, M., Baghani, M., & Bahri, R. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112772
SLA-v3: Exploration by Traversal Difficulty Encouragement
Liu, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38404-1_1
Autonomous racing policy using safety-critical evolution in knowledge-fusion reinforcement learning
Hou, X., 甘明刚, Wu, W., Ma, Q., & Chen, J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116528
Applying deep reinforcement learning to manage mobility in a sliced 6G vehicular network: a survey
Arwa, A., & Zarai, F. (2026) · Cluster Computing · doi:10.1007/s10586-026-06606-8
Role-Aware Representation and Uncertainty-Driven Policy Regularization for UAV Swarm Air Combat
Yang, Q., Li, D., Yan, H., Li, F., & Jia, J. (2026) · International Journal of Aeronautical and Space Sciences · doi:10.1007/s42405-026-01284-7
A Survey of Deep Reinforcement Learning for Intelligent Decision-Making Systems
Thiyagarajan, V., Veerasundari.R, Deepa, S., Saranya, R., Jose, P., & Gunanandhini, S. (2026) · International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG) · doi:10.1109/icstsdg69220.2026.11708319
“…is a combination of RL and DNN. Deep learning allows RL agents to estimate value functions, policies, and state representations with high-capacity models, which is more powerful than classical RL, and allows performance in complex decision-making problems, which previously were infeasible[2-3].”
Berndt, L. C. S., & Shaw, A. D. (2026) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2026.1917153
“Modern reinforcement-learning frameworks can themselves incorporate learned environment models (M. Moerland et al., 2023) and uncertainty-aware, information-seeking exploration objectives (Ladosz et al., 2022).”
Wan, X., & Fu, L. (2026) · International Journal of Mobile and Blended Learning · doi:10.4018/ijmbl.424747
Zhan, J., Yang, Y., Zhang, Z., Liu, Y., Bie, Y., Pei, M., & Qu, X. (2026) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2026.106090
Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
Bei, Y., Zhang, W., Wang, S., Chen, W., Zhou, S., Chen, H., Li, Y., Bu, J., Pan, S., Yu, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2506.18019
“Task decision searching is an important process in the planning stage of AI agents, involving the making of sequential decisions in complex environments to achieve specific goals [148].”
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
