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
Flagged first, then by citations
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 301–400 of 528
Decision-Time Learning and Planning Integrated Control for the Mild Hyperbaric Chamber
Zhang, N., Lin, Q., & Jiang, Z. (2025) · Algorithms · doi:10.3390/a18070380 · Cited by 1
Li, Z. (2025) · International Journal of Knowledge Management · doi:10.4018/ijkm.382385 · Cited by 1
Framework for deep reinforcement learning in Webots virtual environments
Šareiko, A., Mažeika, D., & Laukaitis, A. (2025) · New Trends in Computer Sciences · doi:10.3846/ntcs.2025.23668 · Cited by 3
Wahidi, M., Rizk, A., & Imad, R. (2025) · IEEE Access · doi:10.1109/access.2025.3589514 · Cited by 1
“And while we have already mentioned that the notorious sample inefficiency of RL methods is partially due to a lack of informative feedback from sparse reward signals in the previous section, another reason is the problem of efficiently sampling the right data [54], [129].”
Overcoming Exploration Stagnation in Reinforcement Learning-Based Automated Game Testing
Jang, T.-H., Lee, Y., & Kim, H. S. (2025) · Journal of Digital Contents Society · doi:10.9728/dcs.2025.26.7.1801 · Cited by 1
Architectural Mitigation of Control AI Risk Factors for Safe Human-Robot-Collaboration
Kreutz, A., Beck, R., Weiß, G., & Otsuka, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-02018-5_34 · Cited by 1
Feng, G., Gao, T. Y., Bian, S. B., & Yu, T. (2025) · AIMS Electronics and Electrical Engineering · doi:10.3934/electreng.2025024 · Cited by 1
Gomathi, D., & Harshavarthini, S. (2025) · IEEE Access · doi:10.1109/access.2025.3610459 · Cited by 1
“In this instance, reinforcement learning (RL) is one amongst the predominant techniques to be used in the stabilization process which optimizes the controller and produces effective results [12], [13], [14], [15] and [16].”
Bounded Active Exploration for Model-Based Reinforcement Learning
Qiao, T., Williams, H. A., & MacDonald, B. A. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163912 · Cited by 1
“It promotes efficient exploration by avoiding monotonous patterns [17], thereby making informed decisions about when and how to conduct exploration.”
Guided Exploration Reinforcement Learning for 3D UAV Pursuit-evasion Games
Kim, D., Lee, S., Lee, J. D., Lee, H., & Bang, H. (2025) · International Journal of Control Automation and Systems · doi:10.1007/s12555-025-0071-0 · Cited by 1
“Recent work has shown that imitation-based exploration, where demonstration data or expert trajectories guide initial policy search, can substantially shorten training time and improve final performance [27-29].”
Two-Layered Reward Reinforcement Learning in Humanoid Robot Motion Tracking
Xu, J., Zheng, Z., & Ren, F. (2025) · Mathematics · doi:10.3390/math13213445 · Cited by 1
Adaptive Altitude Control for Underwater Vehicles Based on Deep Reinforcement Learning
Wang, Z., Hou, D., Lu, B., Li, G., Zhang, X., & Liu, Z. (2025) · International Conference on Transportation Information and Safety · doi:10.1109/ictis68762.2025.11214834 · Cited by 1
Ji, X., Pan, C., Yu, M., Jiang, Q., & Fan, Q. (2025) · Journal of Control and Decision · doi:10.1080/23307706.2025.2556991 · Cited by 1
Enhancement of hydrologic model optimization with single-step reinforcement learning
Lee, B., Jeong, H., Lee, Y., McCarty, G. W., Zhang, X., & Lee, S. (2025) · Journal of Hydrology · doi:10.1016/j.jhydrol.2025.134595 · Cited by 1
MAD3PG: A framework for multi-agent deep denoising diffusion policy gradient optimization
Zhong, S., Wang, G., Zhang, J., Wang, X., Teh, K. C., Diao, H., Zhang, P., He, J., Zeng, Z., Cheng, T. H., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.104026 · Cited by 1
Zang, W., Wang, B., Zhang, H., Song, D., & Guo, T. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3618155 · Cited by 1
“Unlike conventional black-box regression, the RL formulation enables policy learning under long-term objective constraints [9] and captures the trajectory-dependent nature of AoA decisions [10].”
Comparative Evaluation of Reasoning and Inference in LLM-Based and Diffusion-Based Approaches
Zhao, W., & Mahmoud, Q. H. (2025) · IEEE Access · doi:10.1109/access.2025.3632686 · Cited by 1
“Ladosz et al. [8] discussed several potential challenges faced by RL exploration in reinforcement learning.”
InfluentialHealth state prediction with reinforcement learning for predictive maintenance
Aglogallos, A., Bousdekis, A., Kontos, S., & Mentzas, G. N. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1720140 · Cited by 1
Liu, J., Shen, X. Q., & Gao, H. (2026) · IEEE Access · doi:10.1109/access.2026.3655347 · Cited by 1
“Specifically, algorithmic innovations such as value decomposition networks, actor–critic architectures tailored for cooperative settings, and credit assignment mechanisms have significantly enhanced performance in high-dimensional, uncertain environments [10], [11], [12].”
Hu, P., Wen, T., Zhang, D., Chen, H., & Gong, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-35391-y · Cited by 2
“The application of Reinforcement Learning (RL) in industrial control systems, particularly in the domain of heavy machinery such as hydraulic excavators, has gained substantial academic and practical interest over recent years 25–29 .”
QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
Thomas, A. M., Chen, Y.-C., Valencia, H., Jose, S. T., & Wu, R. (2025) · IEEE International Conference on Quantum Artificial Intelligence (QAI) · doi:10.1109/qai63978.2025.00029 · Cited by 7
“Reinforcement learning (RL) is an online learning paradigm where an agent learns to take an action by optimising an action policy through interactions with an environment [29].”
Löppenberg, M., Yuwono, S., & Schwung, A. (2026) · AI · doi:10.3390/ai7020062 · Cited by 1
“Based on these principles, we are expanding these strategies and focus on the following challenges: First, RL reaches its limits in complex multi-agent systems, particularly due to high computing costs, slow convergence, and problems with generalization [20,21].”
InfluentialCollaborative Assembly Policy Learning of a Sightless Robot
Zhang, Z., Lu, W., Yang, L., Jing, W. P., Tang, B., & Pan, J. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11377489 · Cited by 1
“Reinforcement learning approaches face the challenge of sparse rewards due to the lack of positive data [23].”
Ye, Y., Zhu, Y., Lin, H., Che, L., & Zhou, H. (2026) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2026.109638 · Cited by 1
VLM-Nav: Mapless UAV navigation using monocular vision driven by vision-language models
Sarker, G. C., Azad, A., Rahman, S., & Hasan, M. M. (2026) · PLoS ONE · doi:10.1371/journal.pone.0345778 · Cited by 1
“RL algorithms also often involve complex reward structures and tuning, which further increases training time [16].”
Multi-neurotransmitter synergistically regulated basal ganglia reinforcement learning model
Zhang, S.-P., Jiang, W.-G., Deng, X., Gu, Y.-H., Yao, N., Liang, X.-L., & Huang, Z.-G. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.108941 · Cited by 1
From simulation to learning: A comprehensive review of multi-agent systems in emergency management
Jin, X., Guo, T., Zhan, D., & Qi, C. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133841 · Cited by 1
Li, Y., Gao, J., & Chen, Y. Z. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3691390 · Cited by 1
“Moreover, designing appropriate reward functions for long-horizon manipulation tasks remains challenging [17].”
Optimal Control of Mobile Energy Storage via Knowledge‐Guided Deep Reinforcement Learning
Cai, X., Meng, Z., Guo, Q., Jiang, L., Shen, Z., Cheng, Y., Gui, X., & Zhao, J. (2026) · Battery energy · doi:10.1002/bte2.70132 · Cited by 1
“DRL enables an agent to learn an optimal control policy through direct trial‐and‐error interaction with its environment, thus bypassing the challenges of precise system modeling [14, 15].”
Multiagent Policy-Sharing and Safety-Aware Action Correction for Multi-ASV Cooperative Encirclement
Wu, Y. N., Tian, S., Tao, W., Ji, Z., & Wei, C. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3709862 · Cited by 1
“Sparse rewards are widely regarded as one of the core challenges for e ff ective learning in MARL, especially in training scenarios where feedback signals are limited [29], [30].”
Leng, B., Zhang, W., Li, Z., Xiong, L., Jin, G., Yu, R., & Lv, C. (2026) · Green Energy and Intelligent Transportation · doi:10.1016/j.geits.2026.100452 · Cited by 1
Lyu, Y., Li, D., Jin, H., Zhang, Y., Jiang, Y., & Yin, Y. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02926-z · Cited by 1
Li, C., Wu, F., & Zhao, J. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-0617-8_18 · Cited by 1
More effective and efficient exploration via more refined gradient information
Chen, X., & Liu, J. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04955-0 · Cited by 1
“(4) Random exploration can prolong the learning time and pose safety concerns due to the repeated random selection of unsafe actions, particularly in real-case scenarios such as robotics [4].”
BackgroundMethodInfluentialTabular Monte Carlo Reinforcement Learning for Valve Position Control
Felisiak, P. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10253420 · Cited by 1
Reward shaping using directed graph convolution neural networks for reinforcement learning and games
Sang, J., Khan, Z. A., Yin, H., & Wang, Y. (2023) · Frontiers in Physics · doi:10.3389/fphy.2023.1310467 · Cited by 1
A Distributed Framework for Deep Reinforcement Learning by Consensus
Liu, B., Zhu, S., Sun, P., Huang, Q., & Ding, Z. (2023) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc58219.2023.10327122 · Cited by 1
“Reinforcement learning refers to an agent exploring an unknown environment to learn an optimal policy for a given task by iteratively trial and learning, which shows great potential in different engineering application fields [1]–[3].”
BackgroundSelf-Supervised Network Distillation for Exploration
Zhang, X., Dai, R., Chen, W., & Qiu, J. (2023) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001423510217 · Cited by 1
Mazaya, M. S., Budi, E. M., Syafalni, I., Sutisna, N., & Adiono, T. (2024) · IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS) · doi:10.1109/coolchips61292.2024.10531164 · Cited by 1
“Exploration of uncharted territory means that the agent will take an explorative action to expand the knowledge of the agent, solving the sparseness of the reward problem [11].”
BackgroundPayment channel fee setting dynamic algorithm based on BiLSTM-PPO
song, C., Li, L., & Gao, H. (2024) · International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT) · doi:10.1117/12.3031220 · Cited by 1
“1) State: The state space represents the information about the environment acquired by the intelligent agent and serves as a crucial basis for the subsequent decision-making and evaluation of returns [7].”
Reinforcement Learning for Medical Image Classification Based on Deep Deterministic Policy Gradients
Chaddad, A., & Jiang, Y. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635454 · Cited by 1
“Our approach incorporates reinforcement learning (RL) [1], which can automatically learn the optimal data transformation strategy and dynamically adjust parameter selection depending on the effect of the current model.”
MethodJin, Z., Chen, R., Wu, K., Yu, T., & Fu, L. (2024) · Drones · doi:10.3390/drones8090462 · Cited by 1
Leguel, A. K. G., Nguyen, H., Gómez‐Gutiérrez, D., Yoo, J., & Jeong, H. (2024) · Sensors · doi:10.3390/s24186086 · Cited by 1
“In DRL, the choice between sparse and dense rewards is critical in determining how effectively an agent learns from its environment [30,31].”
BackgroundChen, S., Cong, X., Zang, H., Fu, Y., Li, H., & Xu, H. (2024) · Applied Physics B · doi:10.1007/s00340-024-08352-4 · Cited by 1
Multi-agent cooperative encirclement based on improved MADDPG algorithm
Ai, L., Tang, S., & Yu, J. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2898/1/012033 · Cited by 1
Distributed Unmanned Aerial Vehicle Cluster Testing Method Based on Deep Reinforcement Learning
Li, D., & Yang, P. (2024) · Applied Sciences · doi:10.3390/app142311282 · Cited by 1
“Ladosz et al. [22] reviewed exploration techniques in deep reinforcement learning.”
Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
Bouchoucha, R., Yahmed, A. H., Patil, D., Rajendran, J., Nikanjam, A., Chandar, S., & Khomh, F. (2024) · IEEE International Conference on Software Maintenance (ICSM) · doi:10.1109/icsme58944.2024.00019 · Cited by 1
“…the use of RL methods for complex state and action spaces, overcoming the limitations of traditional RL. Training a DRL agent presents challenges such as ensuring effective exploration of the environment [32] and stabilizing the training of the function approximators used by the agent [2] [33].”
V2PCP: Toward Online Booking Mechanism for Private Charging Piles
Lu, X., Sun, J., Lou, J., Ji, Y., Wu, C., Zhao, W., Xue, G., Luo, Y., Cheng, F., & Li, J. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3516828 · Cited by 1
“This disparity can be attributed, in part, to the intricate state spaces inherent in complex environments, which pose significant challenges to the exploration capabilities of reinforcement learning agents [49].”
ActionFusion: Framework of Large Action Model Enablement
Shan, R., & Shan, T. C. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825136 · Cited by 1
Worst-Case Execution Time Analysis of Real-Time Robotic Algorithms Using Reinforcement Learning
Samiei, A., Kahani, N., Dehghanitafti, M., & Ahmadi, M. (2024) · IEEE International Conference on Collaborative Advances in Software and Computing (CASCON) · doi:10.1109/cascon62161.2024.10838116 · Cited by 1
Demonstration and offset augmented meta reinforcement learning with sparse rewards
Li, H., Liang, J., Wang, X., Jiang, C., Li, L., & Zeng, D. D. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01785-0 · Cited by 1
“These methods primarily focus on improving exploration and can be broadly classified into two categories: rewarding novel states and rewarding diverse behaviors [2].”
Two-Phase Deep Q Learning Network for Secure Healthcare Model in the Internet of Things
Selvam, D. T., S.Vinothkumar, J. A., & Madhubala, S. (2024) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit64383.2024.10912278 · Cited by 1
“Ladosz et al. [17] outlined unresolved issues and provided recommendations for future research, comparing methods across different categories in terms of overall performance, computational effort, and complexity.”
A learnable dynamic scheduling for directed graph jobs flow in heterogeneous supercomputing clusters
Wang, L., Zhou, J., & Liu, W. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.108047 · Cited by 1
PACER: A fully push-forward-based distributional reinforcement learning algorithm
Bai, W., Zhang, C., Fu, Y., Zhao, P., & Qian, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131301 · Cited by 1
Kadi, H. A., & Terzić, K. (2022) · Preprints.org · doi:10.20944/preprints202212.0305.v1 · Cited by 1
Scalable quasi-static self-modeling for physical legged locomotionPreprint
Hu, Y., Kwiatkowski, R., Chen, B., Wyder, P. M., & Lipson, H. (2023) · Research Square · doi:10.21203/rs.3.rs-3121605/v1 · Cited by 1
Reinforcement Learning Recommendation Algorithm Based on Environmental Information ExplorationPreprint
Jia, J., Wang, H., Fen, W., Li, T., & Liu, S. (2024) · Research Square · doi:10.21203/rs.3.rs-4531402/v1 · Cited by 1
Sustainable Multi-Modal Transit Timetabling with Deep LearningPreprint
Zhang, K., Shi, Y., & Clarke, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4884880 · Cited by 1
Koren, M., Peretz, O., Dinh, T., & Yu, P. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6255269 · Cited by 1
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Chen, T., Lu, S., Zhao, K., Meng, W., Teng, H., Li, T., Li, C., Liu, X., Liang, J., Zhang, Z., et al. (2026) · arXiv
“Under-exploration [16] manifests as a bias toward low-risk local edits: prompt rephrasing, tool-description tuning, or minor control-flow tweaks.”
SNSE: State Novelty Sampling Exploration
Li, S., Luo, X., Zhang, Z., Yu, H., & Xie, S. (2022) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis57298.2022.10016361
A Digital Twin-Based Implementation for Adaptive Traffic Signal Control: A Case StudyPreprint
Çeltek, S. A., Durdu, A., Burak Seyit, K. A. R. A., Unver, S., & Budak, Z. H. Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4508020
Towards Human-Level Safe Reinforcement Learning in Atari Library
Afriyadi, A., & Utomo, W. H. (2023) · Jurnal Sisfokom (Sistem Informasi dan Komputer) · doi:10.32736/sisfokom.v12i3.1739
“…in robotics for safe control of autonomous robots, in gaming for developing safe and fair game-playing agents, and in healthcare for developing personalized treatment [13, 17, 23, 24] provide valuable insights into the practical challenges and solutions for safe RL in real-world applications.”
BackgroundAutonomous and Security-Aware Dynamic Vehicular Platoon Formation
Phillips, D., Halabi, T., & Zulkernine, M. (2023) · International Conference on Dependable Systems and Their Applications (DSA) · doi:10.1109/dsa59317.2023.00109
“Exploration and Rewards: A key part of the training process is the way the agent explores the environment [29].”
BackgroundSeshagiri, S., & Prema, K. V. (2023) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci58599.2023.10331400
“[3] The target policy does the function approximation and path improvement while the behavioural policy is responsible for exploration.”
BackgroundReinforcement-Learning-Based 2D Flow Control for Logistics Systems
Yin, M., Cai, C., & Liu, J. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-1010-2_19
Image Pre-Processing Detection Using Deep Reinforcement Learning
Mukesh, N. M. (2024) · ASIAN JOURNAL OF CONVERGENCE IN TECHNOLOGY · doi:10.33130/ajct.2024v10i01.013
“Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision [15].”
Qi, P., & Zhu, H. (2024) · Cardiff University Engineering Research Conference · doi:10.18573/conf1.x
Accelerating Multi-step Sparse Reward Reinforcement Learning
Yang, X., & Ji, Z. (2024) · Cardiff University Engineering Research Conference · doi:10.18573/conf1.u
“As a result, the default setting of using a strategy that explores constantly or decays the randomness in a task-agnostic way [6] will have di ff iculty dealing with multi-step tasks.”
InfluentialProximity-Based Reward Systems for Multi-Agent Reinforcement Learning
Blais, M.-A., & Akhloufi, M. A. (2024) · International Conference on Image Processing and Robotics (ICIPRoB) · doi:10.1109/iciprob62548.2024.10543232
“A common issue encountered when creating an MARL system is reward sparsity [14].”
BackgroundA Novel Two Step Computer Network Attack and Defense Strategy
Bai, Q. (2024) · International Conference on Inventive Computation Technologies (ICICT) · doi:10.1109/icict60155.2024.10544975
Leveraging Emotion-Mediated Exploration to Adapt Agent Behavior
Assunção, G., Castelo-Branco, M. S., & Menezes, P. J. (2023) · Experiment@International Conference · doi:10.1109/exp.at2358782.2023.10545947
“In terms of learning, reinforcement methodology is the most common adapter of behavior, with agents altering exploration patterns based on reward shaping or event probability availability [4].”
BackgroundCross-Selling Artificial Intelligence-Based Approaches in Insurance Industry: A Review
Aref, S. M., Fouad, M. M., Sayed, H. A., & Gabr, M. I. (2024) · doi:10.1109/iceeng58856.2024.10566415
“The last type is reinforcement learning which is used for unknown environments, it is the mix between unsupervised and semi-supervised learning depending on the selected problem to solve [30].”
BackgroundReducing redundancy of skills in hierarchical reinforcement learning with offline data
Zhou, Y., Wang, X., Wang, X., Xie, S., & Zhang, Z. (2024) · International Conference on Electronic Information Engineering and Data Processing (EIEDP) · doi:10.1117/12.3032877
Chopra, K., Zafar, S., & Yadav, A. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-3588-4_8
DHAA: Distributed heuristic action aware multi-agent path finding in high density scene
Zhou, D., Pang, Z., & Li, W. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19951-w
Efficient Adversarially Guided Actor–Critic
Xu, M., Ge, S. S., Zhao, D., & Zhao, Q. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3453444
“Traditional exploration approaches, such as epsilon-greedy and random action methods, improve sample efficiency in dense reward environments but fall short in sparse reward environments [5].”
Knowledge-Guided Reinforcement Learning for Low-Resource Unsupervised Syllabification
Wang, W., Dong, L., Yu, Z., Huang, Y., Guo, J., & Gao, S. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650807
“Reinforcement learning is currently mainly focused on the research of three types of methods [29]: Markov Decision Process, Value-Based methods, and Policy-Based methods.”
MethodLi, W., Hu, B., Song, A., & Huang, K. (2024) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2024.3470068
“However, the wargame environment usually has quite large state and action spaces as well as very sparse rewards for long-term decision-making, thus presenting a big challenge for conventional MARL approaches [8], [9].”
Chen, Y., Yan, H., & Ding, Z. (2024) · Research Square · doi:10.21203/rs.3.rs-5340149/v1
Reinforcement Learning with Enhanced Bubble Sort for Wireless Mesh Networks Node Selection
Revathy, G., Senthilkumar, J., Gurumoorthi, E., & Shyamalagowri, M. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-75608-5_6
Action-attentive deep reinforcement learning for autonomous alignment of beamlines
Wang, S., Dai, S., Jiang, J., Wu, S., Peng, H., & Zhang, J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115836 · Cited by 1
Double Replay Buffer Mechanism for Deep Reinforcement Learning Algorithm
Ji, Y., Le, W., Tian, X., Liu, G., Han, L., & Cui, T. (2024) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs63941.2024.10800212
“Reward is the feedback signal given by the environment in response to the agent's actions or policies, used to evaluate whether the agent's behavior is correct [2].”
Inferring Reward Functions from State Transitions: A Deep Learning Approach
Perween, T., Roy, S. N., Sadhu, A. K., & Dasgupta, R. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10832068
“A well-chosen reward scale range is crucial for shaping an agent’s behavior and achieving its goal [17].”
Kakavand, M., Baghani, M., Yeganeh, H., & Bahri, R. (2024) · International Symposium on Telecommunications · doi:10.1109/ist64061.2024.10843507
Exploring Ensemble Error Exploration for Unsupervised Reinforcement Learning
Shiman, N., Latyshev, A., Kuderov, P., & Panov, A. I. (2025) · Studies in computational intelligence · doi:10.1007/978-3-031-80463-2_18
Novelty-based Sample Reuse for Continuous Robotics Control
Duan, K., Yang, K., Liu, H., & Wang, X. (2024) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio64047.2024.10907722 · Cited by 1
“Exploration encourages agents to gather diverse data by probing uncharted areas of the environment, which helps prevent local convergence and aids in finding global optimal solutions [18].”
BoxesZero: An Efficient and Computationally Frugal Dots-and-Boxes Agent
Niu, X., Liu, Q., Chen, W., Zheng, Y., & Jin, Z. (2025) · Entropy · doi:10.3390/e27030285
“Incorporating Domain Knowledge : In reinforcement learning, effectively utilizing prior knowledge without hindering exploration embodies the balance between explo-Entropy ration [24] and exploitation, which is a significant challenge.”
A New Path Planning Algorithm for Marine Engine Room Inspection Based on RA*-ADWA*
Gong, Y., Li, R., Guo, J., & Song, E. (2024) · International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI) · doi:10.1109/ricai64321.2024.10911335
“Although the reinforcement learning methods have excellent learning performance, but the training process requires significant computational power [19].”
DDPG-MPC: A Safe and Efficient Hybrid Path Planning Algorithm for Robots
Ding, A., Sun, L., Han, M., Guo, Z., Wang, T., & Ma, H. (2024) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac63491.2024.10919372
“The design of the reward function determines the effectiveness of RL [23].”
Quadruped Robot System Based on Proprioceptive Vision and Complex Ground Mobility Capabilities
Ling, X., Yuan, H., Li, S., & Tang, B. H. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-3349-4_23
Liu, Y., Zhang, J., Wang, C., Li, D., Lv, T., & Chen, Z. (2024) · Asia-Pacific Artificial Intelligence and Big Data Forum (AIBDF) · doi:10.1145/3718491.3718656
“To enable each agent to autonomously learn and optimize its behavior, we apply a reinforcement learning (RL) [21] algorithm.”
Model-Based Reinforcement Learning for Connected and Automated Vehicles Platoon Control
Yan, Y., Min, H., & Fang, Y. (2024) · IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI) · doi:10.1109/soli63266.2024.10956079
“Exploitation involves choosing actions that currently appear to be the best; exploration, however, involves trying different actions to uncover new strategies that may yield greater rewards [14].”
Yang, J., Gao, T., & Shengnan, S. (2025) · International Journal of High Speed Electronics and Systems · doi:10.1142/s0129156425404693
Exploration in Case-Based Reasoning for Improved Problem-Solving
Boulmaiz, F., Reignier, P., & Ploix, S. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-5887-9_24
Gao, Z., Wong, P. K., & Zhao, J. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-3317-3_38
Examination of Teacher Candidates’ Intercultural Sensitivity Levels by CART Analysis
SÖYLEMEZ, N. H. (2025) · SAGE Open · doi:10.1177/21582440251334441
“Reinforcement learning relies on interaction with an environment, where the model learns by receiving feedback in the form of rewards or penalties (Ladosz et al., 2022).”
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
