Cooperative Multi-Agent Learning: The State of the Art
The DOI matches its Crossref record; 324 of the 327 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Integration ensures that machine outputs are used to challenge humans, and human inputs to challenge machines (Hoc, 2001), allowing for mutual learning (Panait & Luke, 2005) and debiasing (Larrick, 2004).”
From Artificial Intelligence and Management: The Automation–Augmentation Paradox (2021) · cites this paper as Panait & Luke, 2005
In the citing paper
“For example, AI is often applied in open systems, blurring organizational boundaries (Panait & Luke, 2005).”
From Artificial Intelligence and Management: The Automation–Augmentation Paradox (2021) · cites this paper as Panait & Luke, 2005
In the citing paper
“Multi-agent RL can also be applied to understand the behavior of groups of agents who need to cooperate; see [607] for an overview and [385,475] for recent examples.”
From Tackling climate change with machine learning (2023) · cites this paper as [607]
Citations
Cites
Genetic algorithms in search, optimization, and machine learning
(1989) · Choice Reviews Online · doi:10.5860/choice.27-0936 · Cited by 49,010
Holland, J. H. (1992) · The MIT Press eBooks · doi:10.7551/mitpress/1090.001.0001 · Cited by 47,002 · cited 1×
“There are many sources of additional information on EC; good choices include [6, 63, 64, 81, 87, 114, 141, 164].”
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 2×
“Other games have included Tic-Tac-Toe [4], Mancala [61], Othello [241], Go [149], Chess [138, 269], Poker [139], Blackjack [261], Nim and 3D Tic-TacToe [219], and Tag [215].”
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Axelrod, R., & Hamilton, W. D. (1981) · Science · doi:10.1126/science.7466396 · Cited by 20,065
Genetic Algorithms in Search, Optimization and Machine Learning
Goldberg, D. E., & Robson, D. (1988) · Cited by 18,391
Goldberg, D. E., & Shakespeare, W. (2002) · Cited by 16,088
Genetic Programming: On the Programming of Computers by Means of Natural Selection
Koza, J. R. (1992) · Medical Entomology and Zoology · Cited by 13,082
Genetic Algorithms + Data Structures = Evolution Programs
Michalewicz, Z. (1992) · Artificial Intelligence · doi:10.1007/978-3-662-02830-8 · Cited by 11,553
Goldberg, D. E. (1989) · Medical Entomology and Zoology · Cited by 10,109
Research works printed but not linked: 36
- W. Arthur, 1994, Complex. Econ. Theory, 84, 406
- B. Banerjee, R. Mukherjee, and S. Sen. “Learning mutual trust,” in Working Notes of AGENTS-00 Workshop on Deception, Fraud and Trust in Agent Societies, pp. 9–14, 2000.
- J. K. Bassett, 2002, A study of generalization techniques in evolutionary rule learning
- D. Bernstein, S. Zilberstein, and N. Immerman, “The complexity of decentralized control of MDPs,” in Proceedings of UAI-2000: The Sixteenth Conference on Uncertainty in Artificial Intelligence, 2000.
- L. Bull and O. Holland, “Evolutionary computing in multiagent environments: Eusociality”, in Proceedings of Seventh Annual Conference on Genetic Algorithms, 1997.
- M.R. Cutkosky, 1997, Readings in Agents, 46
- F. Fernandez, 2001, Int. J. Robot. Autom., 16, 217
- B. M. Good, Evolving multi-agent systems: Comparing existing approaches and suggesting new directions, Master’s thesis, University of Sussex, 2000
- D. L. Grecu, Using Learning to Improve Multi-Agent Systems for Design. PhD thesis, Worcester Polytechnic Institute, 1997
- J. Grefenstette, 1990, Machine Learn., 5, 355
- S.M. Gustafson, 2000, Layered learning in genetic programming for a co-operative robot soccer problem
- Haynes T., 1995, Adaptation and Learning in Multiagent Systems, Lecture Notes in Artificial Intelligence
- T. Haynes and S. Sen, “Crossover operators for evolving a team,” in J. R. Koza, K. Deb, M. Dorigo, D. B. Fogel, M. Garzon, H. Iba, and R. L. Riolo, (eds.), Genetic Programming 1997: Proceedings of the Second Annual Conference, Morgan Kaufmann: Stanford University, CA, USA, pp. 162–167, 13–16 July 1997
- D. Hillis, 1991, Artif. Life II, SFI Stud. Sci. Complex., 10, 313
- J. Holland, 1975, Adaptation in Natural and Artificial Systems
- J. Hu, 2003, J. Machine Learn. Res., 4, 1039
- M. Huhns and M. Singh, “Agents and multiagent systems: Themes, approaches and challenges,” in’M. Huhns and M. Singh, (eds.), Readings in Agents, Morgan Kaufmann, pp. 1–23, 1998
- I. Imam, (ed.), Intelligent Adaptive Agents. Papers from the 1996 AAAI Workshop. Technical Report WS-96-04, AAAI Press, 1996
- A. Ito, “How do selfish agents learn to cooperate?,” in Artificial Life V: Proceedings of the Fifth International Workshop on the Synthesis and Simulation of Living Systems, MIT Press, pp. 185–192, 1997
- L. R. Leerink, S. R. Schultz, and M. A. Jabri, “A reinforcement learning exploration strategy based on ant foraging mechanisms,” in Proceedings of the Sixth Australian Conference on Neural Networks, Sydney, Australia, 1995
- S. Luke, “Genetic programming produced competitive soccer softbot teams for RoboCup97,” in J. R. Koza et al, (ed.), Genetic Programming 1998: Proceedings of the Third Annual Conference, Morgan Kaufmann, pp. 214–222, 1998
- M. Mitchell, J. Crutchfield, and R. Das, “Evolving cellular automata with genetic algorithms: A’review of recent work,” in Proceedings of the First International Conference on Evolutionary Computation and its Applications (EvCA’96), 1996
- N. D. Monekosso, P. Remagnino, and A. Szarowicz, “An improved Q-learning algorithm using synthetic pheromones,” in Proceedings of the Second Workshop of Central and Eastern Europe on Multi-Agent Systems CEEMAS-01, pp. 197–206, 2001 · DOI
- J. Pollack, 1997, Artificial Life V: Proc. of the Fifth Int. Workshop on the Synthesis and Simulation of Living Systems, 92
- J. Schmidhuber, “Realistic multi-agent reinforcement learning,” in Learning in Distributed Artificial Intelligence Systems, Working Notes of the 1996 ECAI Workshop, 1996
- A. Schultz, J. Grefenstette, and W. Adams, “Robo-shepherd: Learning complex robotic behaviors,” in Robotics and Manufacturing: Recent Trends in Research and Applications. Vol. 6, ASME Press, pp. 763–768, 1996
- M. Sekaran and S. Sen, “To help or not to help”, in Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society, Pittsburgh, PA, pp. 736–741, 1995
- L. Spector and J. Klein, “Evolutionary dynamics discovered via visualization in the breve simulation environment,” in Workshop Proceedings of the 8th International Conference on the Simulation and Synthesis of Living Systems, pp. 163–170, 2002
- L. Steels, 1996, Machine Intelligence 15
- P. Stone, “Layered learning in multiagent systems,” in Proceedings of National Conference on Artificial Intelligence AAAI/IAAI, 1997
- P. Stone, “Layered Learning in Multi-Agent Systems,” PhD thesis, Carnegie Mellon University, 1998
- R. Sutton, 1998, Machine Learn., 3, 9
- P. ’t Hoen and K. Tuyls, “Analyzing multi-agent reinforcement learning using evolutionary dynamics,” in Proceedings of the 15th European Conference on Machine Learning (ECML), 2004
- M. Tan, 1993, Readings in Agents, 487
- J. Werfel, November 2000, IEEE Trans. Evol. Comput., 4, 388
- T. White, 1998, Genetic Programming 1998: Proceedings of the Third Annual Conference, 22
Cited by
Items 101–200 of 1,000
The Measure of All Minds: Evaluating Natural and Artificial Intelligence
Hernández‐Orallo, J. (2017) · Cited by 88
Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games
Wang, J., Zhang, Y., Kim, T., & Gu, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6220 · Cited by 194
“The global reward game with this credit assignment scheme is also called shared reward game (also known as fully cooperative game) (Panait and Luke 2005).”
BackgroundGenerating Long-term Trajectories Using Deep Hierarchical Networks
Zheng, S., Yue, Y., & Lucey, P. (2017) · CaltechAUTHORS (California Institute of Technology) · doi:10.48550/arxiv.1706.07138 · Cited by 80
“We only modeled offensive players: an interesting direction is modeling defensive players and integrating adversarial reinforcement learning (Panait and Luke [13]) into our approach.”
BackgroundCooperative multi-robot patrol with Bayesian learning
Portugal, D., & Rocha, R. P. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9503-7 · Cited by 87
“In general, reward-based learning methods are quite attractive since agents are programmed through reward and pun-ishments without explicitly specifying how the task is to be achieved (Panait and Luke 2005).”
BackgroundMulti-agent role allocation: issues, approaches, and multiple perspectives
Campbell, A., & Wu, A. S. (2010) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-010-9127-4 · Cited by 101
“More on machine learning techniques in multi-agent systems can be found in Panait and Luke’s [118] and Stone and Veloso’s [150] surveys of the topic.”
Integration of Machine Learning and Optimization for Robot Learning
Mosavi, A. H., & Várkonyi-Kóczy, A. R. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-46490-9_47 · Cited by 80
“Further most notable ML technologies utilized in Robotics include; ML techniques for big data [20], self-supervised learning [16], reinforcement learning [21], and multi-agent learning [22].”
MethodHeuristically-Accelerated Multiagent Reinforcement Learning
Bianchi, R. A. C., Martins, M. F., Ribeiro, C. H. C., & Costa, A. H. R. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2253094 · Cited by 78
“In addition, a substantial amount of studies [23]–[28] presented surveys in the topic of MRL, discussing propositions on MGs and alternative approaches.”
BackgroundA cluster-based vehicular cloud architecture with learning-based resource management
Arkian, H. R., Atani, R. E., Diyanat, A., & Pourkhalili, A. (2015) · The Journal of Supercomputing · doi:10.1007/s11227-014-1370-z · Cited by 74
“Fortunately, the reinforcement learning techniques [26] can tackle these problems.”
BackgroundYazan, D. M., Yazdanpanah, V., & Fraccascia, L. (2020) · Business Strategy and the Environment · doi:10.1002/bse.2488 · Cited by 82
Karr, J. R., Williams, A. H., Zucker, J., Raue, A., Steiert, B., Timmer, J., Kreutz, C., Wilkinson, S., Allgood, B., Bot, B. M., et al. (2015) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1004096 · Cited by 79
“It uses multiple agents, each simultaneously employing the same algorithm on different regions, to quickly identify optima [22,23].”
BackgroundFrequency adjusted multi-agent Q-learning
Kaisers, M., & Tuyls, K. (2010) · doi:10.5555/1838206.1838250 · Cited by 70
Huang, Z., Yu, H., Peng, Z., & Feng, Y. (2017) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2017.04.004 · Cited by 72
Shapley Q-value:: A Local Reward Approach to Solve Global Reward Games
Wang, J., Zhang, Y., Kim, T., & Gu, Y. (2020) · Research Explorer (The University of Manchester) · Cited by 69
Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective
Panait, L., Tuyls, K., & Luke, S. (2008) · Research Publications (Maastricht University) · Cited by 67
Self-citationPayoff based dynamics for multi-player weakly acyclic games
Marden, J. R., Young, H. P., Arslan, G., & Shamma, J. S. (2007) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2007.4434401 · Cited by 66
“or survey article [ 18 ] for perspectives from machine learning.) Unlike most of the learning rules in this”
BackgroundLearning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
Feng, J., Li, H., Huang, M., Liu, S., Ou, W., Wang, Z., & Zhu, X. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186165 · Cited by 71
“In multi-agent reinforcement learning (MARL) problems [4, 22, 31, 36], there are a group of autonomous, interacting agents sharing a common environment.”
BackgroundDubé, S., & Anctil, D. (2021) · International Journal of Social Robotics · doi:10.1007/s12369-020-00706-0 · Cited by 66
“…it is essential to understand that erobots are not just their perceived characters (e.g., Harmony’s VR character or robotic-headed doll), but are composed of vast interconnected, multi-layered, and (increasingly adaptative) multi-agent systems that enable their (emerging) capabilities [161, 228].”
BackgroundPesce, E., & Montana, G. (2020) · Machine Learning · doi:10.1007/s10994-019-05864-5 · Cited by 96
“The problem of reinforcement learning in cooperative environments has been studied extensively (Littman, 1994; Schmidhuber, 1996; Panait and Luke, 2005; Matignon et al., 2007).”
BackgroundEvolutionary Population Curriculum for Scaling Multi-Agent Reinforcement LearningPreprint
Long, Q., Zhou, Z., Gupta, A., Fang, F., Wu, Y., & Wang, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.10423 · Cited by 137
“Multi-Agent Reinforcement Learning: It has been a long history in applying RL to multi-agent games (Littman, 1994; Shoham et al., 2003; Panait & Luke, 2005; Wright et al., 2019).”
Wachi, A. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/832 · Cited by 83
Multi-agent Reinforcement Learning for Intrusion Detection
Servin, A., & Kudenko⋆, D. (2008) · Springer eBooks · doi:10.1007/978-3-540-77949-0_15 · Cited by 63
“in the applicability of MARL to problems in real world domains [132, 21, 30].”
BackgroundInfluentialSupervision via competition: Robot adversaries for learning tasks
Pinto, L., Davidson, J., & Gupta, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989190 · Cited by 63
“Multi-agent systems [27], [28] are often formulated as a cooperative game.”
BackgroundLi, T., & Zhang, J. (2007) · Automatica · doi:10.1016/j.automatica.2007.07.007 · Cited by 63
“How to exploit the learning ability of agents (Panait & Luke, 2005) to adaptively improve the models and system performances in a distributed way is also an important issue to be studied for MAS.”
BackgroundAgent-based day-to-day adjustment process to evaluate dynamic flexible transport service policies
Djavadian, S., & Chow, J. Y. J. (2016) · Transportmetrica B Transport Dynamics · doi:10.1080/21680566.2016.1190674 · Cited by 63
Two Body Problem: Collaborative Visual Task Completion
Jain, U., Weihs, L., Kolve, E., Rastegari, M., Lazebnik, S., Farhadi, A., Schwing, A. G., & Kembhavi, A. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00685 · Cited by 62
“Similarly, a variety of settings from multiple cooperative agents to multiple competitive ones have been investigated [51, 65, 57, 11, 63, 35, 56, 29, 61].”
BackgroundWang, X., D’Ariano, A., Su, S., & Tang, T. (2023) · Transportation Research Part B Methodological · doi:10.1016/j.trb.2023.02.015 · Cited by 60
A Multiagent Q-Learning-Based Optimal Allocation Approach for Urban Water Resource Management System
Ni, J., Liu, M., Ren, L., & Yang, S. X. (2013) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2012.2229978 · Cited by 63
“The relevant factors in various aspects (such as the development condition of social economy, water demand, and water resource protection) must be considered in the decision making of water resource allocation.”
BackgroundEvolutionary Computation for Reinforcement Learning
Whiteson, S. (2012) · Adaptation, learning, and optimization · doi:10.1007/978-3-642-27645-3_10 · Cited by 70
“The most obvious application of cooperative coevolution is to cooperative multiagent systems (Panait and Luke, 2005) which, in the context of reinforcement learning , means evolving teams of agents that coordinate their behavior to solve a sequential decision problem.”
BackgroundResilience-Oriented Coordination of Networked Microgrids: A Shapley Q-Value Learning Approach
Qiu, D., Wang, Y., Wang, J., Zhang, N., Štrbac, G., & Kang, C. (2023) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2023.3276827 · Cited by 66
“This motivates us to apply the concept of credit assignment [30] that can efficiently distribute the global reward to agents according to their contributions.”
BackgroundMethodDistributed Cooperative Q-Learning for Power Allocation in Cognitive Femtocell Networks
Saad, H., Mohamed, A. M. S., & ElBatt, T. (2012) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2012.6399230 · Cited by 59
“Although, this may lead to oscillations and convergence problems, the IL paradigm showed good results in many applications [10].”
Learning to flock through reinforcement
Durve, M., Peruani, F., & Celani, A. (2020) · Physical Review E · doi:10.1103/physreve.102.012601 · Cited by 58
Effects of Social Network Topology and Options on Norm Emergence
Sen, O., & Sen, S. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14962-7_14 · Cited by 61
“In our formulation, norms evolve as agents learn from their interactions with other agents in the society using multiagent reinforcement learning algorithms [27].”
BackgroundMultiagent Learning of Coordination in Loosely Coupled Multiagent Systems
Yu, C., Zhang, M., Ren, F., & Tan, G. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2387277 · Cited by 59
“in the research community in recent years [10]–[14].”
BackgroundCognition and Docition in OFDMA-Based Femtocell Networks
Galindo‐Serrano, A., Giupponi, L., & Döhler, M. (2010) · Globecom · doi:10.1109/glocom.2010.5683552 · Cited by 57
“In this case, the convergence to optimality proof does not hold strictly, but such an independent learning approach has been shown to correctly converge in multiple applications [ 8 ].”
BackgroundAdaptive Forwarding Delay Control for VANET Data Aggregation
Yu, B., Xu, C., & Guo, M. (2011) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2011.102 · Cited by 57
“Ç”
Decentralized Reinforcement Learning of Robot Behaviors
Leottau, D. L., Ruíz-del-Solar, J., & Babuška, R. (2017) · Artificial Intelligence · doi:10.1016/j.artint.2017.12.001 · Cited by 58
“One of the first mentions of DRL is by Busoniu, De-Schutter, and Babuska [7], where it was used to differentiate a decentralized system from a MAL system composed of individual agents [34].”
BackgroundCoordinating metaheuristic agents with swarm intelligence
Aydın, M. E. (2010) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-010-0435-y · Cited by 58
“On the other hand, the idea of multi agency eases building collaboration among various methods and approaches in a form of collaborating independent computational entities (Panait and Luke 2005; Vazquez-Salceda et al. 2005; Kolp et al. 2006).”
BackgroundLaghari, S., & Niazi, M. A. (2016) · PLoS ONE · doi:10.1371/journal.pone.0146760 · Cited by 56
“Technically, this heterogeneous agent environment collectively forms a cooperative multiagent system [44].”
BackgroundIs multiagent deep reinforcement learning the answer or the question? A brief surveyPreprint
Hernández-Leal, P., Kartal, B., & Taylor, M. E. (2018) · arXiv (Cornell University) · Cited by 56
Su, B., D’Ariano, A., Su, S., Wang, X., & Tang, T. (2023) · Computers & Industrial Engineering · doi:10.1016/j.cie.2023.109742 · Cited by 55
Emergence of conventions through social learning: Heterogeneous learners in complex networks
Airiau, S., Sen, S., & Villatoro, D. (2013) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-013-9237-x · Cited by 54
“We use agents that use multiagent reinforcement learning algorithms [28,35] to adapt their behavior based on their interactions with other agents in the society.”
MethodExploring e-Learning Knowledge Through Ontological Memetic Agents
Acampora, G., Loia, V., & Gaeta, M. (2010) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2010.936306 · Cited by 55
“(or the system is effectively reduced to a monolithic system) [12].”
BackgroundOperation scheduling in a solar thermal system: A reinforcement learning-based framework
Correa-Jullian, C., Droguett, E. L., & Cardemil, J. M. (2020) · Applied Energy · doi:10.1016/j.apenergy.2020.114943 · Cited by 57
Collaborative reinforcement learning for a two-robot job transfer flow-shop scheduling problem
Arviv, K., Stern, H. I., & Edan, Y. (2015) · International Journal of Production Research · doi:10.1080/00207543.2015.1057297 · Cited by 54
Multiagent study of smart grid customers with neighborhood electricity trading
Kahrobaee, S., Rajabzadeh, R. A., Soh, L. K., & Asgarpoor, S. (2014) · Electric Power Systems Research · doi:10.1016/j.epsr.2014.02.013 · Cited by 57
Reaching pareto-optimality in prisoner’s dilemma using conditional joint action learning
Banerjee, D., & Sen, S. (2007) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-007-0020-8 · Cited by 69
“Though Vidal and Durfee explicitly models the influence of a player’sactiononotherstheircalculationsrequiremoreinformationthanweassumeis available[30].Foramorecompletelistofmultiagentreinforcementlearningresearch, refer to recent surveys of the literature[ 21 ;28].”
Decentralized Reinforcement Learning Control of a Robotic Manipulator
Buşoniu, L., Schutter, B. D., & Babuška, R. (2006) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2006.345351 · Cited by 53
“A significant body of research on multi-agent RL has evolved over the last decade (see e.g., [7], [9], [10]).”
On Learning in Collective Self-Adaptive Systems: State of Practice and a 3D Framework
D’Angelo, M., Gerasimou, S., Ghahremani, S., Grohmann, J., Nunes, I., Pournaras, E., & Tomforde, S. (2019) · International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) · doi:10.1109/seams.2019.00012 · Cited by 65
“Existing surveys on multi-agent learning are restricted to reviewing alternative techniques proposed in this context [17], [22], [23].”
BackgroundMulti-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward
Sheikh, H. U., & Bölöni, L. L. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206879 · Cited by 66
“Cooperative multi-agent learning is important since many real-world problems can be formulated as distributed systems with decentralized agents that must coordinate to achieve shared objectives [21].”
BackgroundPIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement LearningPreprint
Liu, I.-J., Yeh, R. A., & Schwing, A. G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00025 · Cited by 66
Multi-UAV planning for cooperative wildfire coverage and tracking with quality-of-service guarantees
Seraj, E., Silva, A., & Gombolay, M. (2022) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-022-09566-6 · Cited by 55
“While the problem of multi-agent planning and scheduling has been studied extensively in prior work [18, 19, 20, 21, 22, 23], many of these works either lack the ability to actively plan in a dynamic environment, or do not provide a probabilistic performance guarantee that assures the teams’…”
BackgroundTo teach or not to teach?: decision making under uncertainty in ad hoc teams
Stone, P., & Kraus, S. (2010) · doi:10.5555/1838206.1838223 · Cited by 53
Norm emergence under constrained interactions in diverse societies
Mukherjee, P. S., Sen, S., & Airiau, S. (2008) · doi:10.5555/1402298.1402332 · Cited by 50
Bui, V., Hussain, A., & Kim, H.-M. (2019) · Energies · doi:10.3390/en12091789 · Cited by 50
“This method drives the learning process based on penalties or rewards assessed on a sequence of actions taken in response to the environment dynamics [17,18].”
MethodHierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery
Yang, J., Borovikov, I., & Zha, H. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/fmju3241 · Cited by 116
Distributed Reinforcement Learning via Gossip
Mathkar, A. S., & Borkar, V. S. (2016) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2016.2585302 · Cited by 52
“(See, e.g., Lauer and Riedmiller (2000), Littman and Boyan (1993), Pendrith (2000), Weiss (1995), also Busoniu et al (2008) and Panait and Luke (2005) for surveys.”
BackgroundDesigning of on line intrusion detection system using rough set theory and Q-learning algorithm
Sengupta, N., Sen, J., Sil, J., & Saha, M. (2013) · Neurocomputing · doi:10.1016/j.neucom.2012.12.023 · Cited by 49
“Huge computational cost is involved to form the modules and centralized communication between the agents fail to develop a robust system.”
BackgroundLiu, R., Yabansu, Y. C., Yang, Z., Choudhary, A., Kalidindi, S. R., & Agrawal, A. (2017) · Integrating materials and manufacturing innovation · doi:10.1007/s40192-017-0094-3 · Cited by 59
“The research on multi-agent learning has been pursued by the machine learning community but was mainly limited to reward-based reinforcement learning problems [51].”
BackgroundMulti-Agent Determinantal Q-LearningPreprint
Yang, Y., Wen, Y., Chen, L., Wang, Y.-X., Shao, K., Mguni, D., & Zhang, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01482 · Cited by 63
“In this work, we consider the multi-agent cooperative setting (Panait & Luke, 2005) where a team of agents collaborate to achieve one common goal in a partially observed environment.”
MethodKaven, L., Huke, P., Göppert, A., & Schmitt, R. H. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02309-8 · Cited by 58
“(Panait & Luke, 2005) On the other hand, competitive agents have contradicting goals and compete against each other.”
Wang, C., Li, J., Jing, N., Wang, J., & Hao, C. H. E. N. (2011) · Chinese Journal of Aeronautics · doi:10.1016/s1000-9361(11)60057-5 · Cited by 47
A Cordial Sync: Going Beyond Marginal Policies for Multi-agent Embodied Tasks
Jain, U., Weihs, L., Kolve, E., Farhadi, A., Lazebnik, S., Kembhavi, A., & Schwing, A. G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58558-7_28 · Cited by 87
Integrating Reinforcement Learning with Multi-Agent Techniques for Adaptive Service Composition
Wang, H., Chen, X., Wu, Q., Yu, Q., Hu, X., Zheng, Z., & Bouguettaya, A. (2017) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3058592 · Cited by 62
“In view of superiority from RL and multi-agent technologies, a natural idea to achieve self-adaptability in a dynamic environment and maintain acceptable efficiency when faced with massive candidate services is to combine them together, which has already been discussed in the field of DAI and is called Multi-agent rei…”
BackgroundDeep Learning Toward Autonomous Ship Navigation and Possible COLREGs Failures
Perera, L. P. (2019) · Journal of Offshore Mechanics and Arctic Engineering · doi:10.1115/1.4045372 · Cited by 52
“reinforcement learning) [7] can be incorporated.”
Li, H., Zhang, J., Zhao, H., Ni, Y., Xiong, J., & Wei, J. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3326808 · Cited by 49
“In multi-agent Markov game, single compound agent training or multi-agent centralized training requires a large-scale neural network and massive parameters, which may lead poor performance in training convergence and model generalization [44], [45].”
BackgroundGESwarm: grammatical evolution for the automatic synthesis of collective behaviors in swarm robotics
Ferrante, E., Duéñez-Guzmán, E., Turgut, A. E., & Wenseleers, T. (2013) · Proceedings of the 15th annual conference on Genetic and evolutionary computation · doi:10.1145/2463372.2463385 · Cited by 44
“In the multi-robot systems and swarm robotics, however, less success has been reported (the reader can refer to the review in [22]).”
BackgroundHybrid online learning control in networked multiagent systems: A survey
Poveda, J. I., Benosman, M., & Teel, A. R. (2018) · International Journal of Adaptive Control and Signal Processing · doi:10.1002/acs.2866 · Cited by 44
Zhou, Z., & Xu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.141 · Cited by 48
Evaluating and modelling Hanabi-playing agents
Walton-Rivers, J., Williams, P. R., Bartle, R. A., Pérez-Liébana, D., & Lucas, S. M. (2017) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2017.7969465 · Cited by 43
Xie, X., Lu, Q., Herrera, M., Yu, Q., Parlikad, A. K., & Schooling, J. M. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2021.102804 · Cited by 41
“Considering the increased complexity caused by multiple participants’ behavioural sophistication (Panait & Luke, 2005), the intelligent agents needs to be completely retrained after understanding the emerging post-pandemic situation.”
BackgroundA Reinforcement Learning Based Solution for Self-Healing in LTE Networks
Moysen, J., & Giupponi, L. (2014) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2014.6965842 · Cited by 48
“TD learning schemes can be demonstrated to achieve optimal solutions, in stationary scenarios with only one decision maker, even though in practice they have been shown to provide successful results also in multi agent scenarios [12].”
BackgroundDistributed W-Learning: Multi-Policy Optimization in Self-Organizing Systems
Dusparic, I., & Cahill, V. (2009) · 2009 Third IEEE International Conference on Self-Adaptive and Self-Organizing Systems · doi:10.1109/saso.2009.23 · Cited by 40
“Multi-agent learning and associated issues have been the subject of extensive research in the area of distributed artificial intelligence [15], [9].”
BackgroundAn approach to multi-agent pursuit evasion games using reinforcement learning
Bilgin, A. T., & Kadioglu-Urtis, E. (2015) · International Conference on Advanced Robotics (ICAR) · doi:10.1109/icar.2015.7251450 · Cited by 42
“It would not be possible to observe this using team learning technique, as it would require the agents to report their findings to a mastermind and wait for a command to take an action [21].”
BackgroundMOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning
da Silva, F. L., Glatt, R., & Costa, A. H. R. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2781130 · Cited by 41
“On the other hand, distributed Q-learning (DQL) [28] can be used to learn an optimal joint policy for cooperative scenarios (also called multiagent MDPs [28], in which R1 = · · · = Rm [29]), with only little computational complexity at each step.”
MethodEvolving Intrinsic Motivations for Altruistic Behavior
Wang, J. X., Hughes, E., Fernando, C., Czarnecki, W. M., Duéñez‐Guzmán, E. A., & Leibo, J. Z. (2019) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/vtgr9509 · Cited by 96
Efficient Training Techniques for Multi-Agent Reinforcement Learning in Combat Tasks
Zhang, G., Li, Y., Xu, X., & Dai, H. (2019) · IEEE Access · doi:10.1109/access.2019.2933454 · Cited by 43
D++: Structural credit assignment in tightly coupled multiagent domains
Rahmattalabi, A., Chung, J. J., Colby, M. K., & Tumer, K. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759651 · Cited by 41
“It consists of a set of homogeneous rovers on a two dimensional plane that must observe a set of POIs within a given time window [1], [5].”
BackgroundAutonomously Reusing Knowledge in Multiagent Reinforcement Learning
Silva, F. L. D., Taylor, M. E., & Costa, A. H. R. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/774 · Cited by 39
Exploration-exploitation in multi-agent learning: Catastrophe theory meets game theory
Leonardos, S., & Piliouras, G. (2022) · Artificial Intelligence · doi:10.1016/j.artint.2021.103653 · Cited by 39
Evolution of Altruistic Robots
Floreano, D., Mitri, S., Pérez-Uribe, A., & Keller, L. (2008) · Springer eBooks · doi:10.1007/978-3-540-68860-0_11 · Cited by 47
“The choice of level of selection is rarely discussed explicitly despite the fact that fitness distribution leads to credit assignment problems [9, 19] in many cooperative multi-agent tasks because individual contributions to team performance are often difficult to estimate or difficult to monitor [23].”
BackgroundHu, G., Li, Y., Li, X., Zhang, G., Zhang, Z., Wang, X., & Man, W. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.03.012 · Cited by 45
Incremental Clustering and Expansion for Faster Optimal Planning in Dec-POMDPs
Oliehoek, F. A., Spaan, M. T. J., Amato, C., & Whiteson, S. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3804 · Cited by 55
“All rights reserved. agent (Huhns, 1987; Sycara, 1998; Panait & Luke, 2005; Vlassis, 2007; Buşoniu, Babuška, & De Schutter, 2008).”
Wang, H., Chen, X., Wu, Q., Yu, Q., Zheng, Z., & Bouguettaya, A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-45391-9_11 · Cited by 38
“As a subdiscipline of distributed artificial intelligence (DAI) [15], multi-agent techniques have arisen as a viable solution for modularity, more computing power, scalability and flexibility required by service composition [16].”
BackgroundComplex agent networks explaining the HIV epidemic among homosexual men in Amsterdam
Mei, S., Sloot, P. M. A., Quax, R., Zhu, Y., & Wang, W. (2010) · Mathematics and Computers in Simulation · doi:10.1016/j.matcom.2009.12.008 · Cited by 38
Chen, G. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/wlnk1814 · Cited by 60
When Machine Learning Meets Geospatial Data: A Comprehensive GeoAI Review
Boutayeb, A., Lahsen-Cherif, I., & Khadimi, A. E. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3568715 · Cited by 68
Multi-Agent Reinforcement Learning for Intrusion Detection: A Case Study and Evaluation
Servin, A., & Kudenko⋆, D. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87805-6_15 · Cited by 37
Breaking into BIM: Performing static and dynamic security analysis with the aid of BIM
Porter, S. R., Tan, T. P. L., Tan, T., & WEST, G. A. W. (2014) · Automation in Construction · doi:10.1016/j.autcon.2013.12.002 · Cited by 41
“Consider that if each agent was to have a complete knowledge of the world, then the behaviour of the system would be akin to a centralized decision maker working through the lower level actuators and sensors [15].”
BackgroundKovalenko, I., Balta, E. C., Tilbury, D. M., & Barton, K. L. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3156384 · Cited by 36
“Using the definitions in [30], [31], we refer to direct cooperation between two agents as the utilization of a one-to-one communication link between the agents for the exchange of information.”
BackgroundLe, T. T., Priya, J. C., Le, H. C., Le, N. V. L., Duong, M. T., & Cao, D. N. (2024) · International Journal of Renewable Energy Development · doi:10.61435/ijred.2024.60119 · Cited by 49
“This strategy motivates learning via the use of rewards or penalties based on a series of actions in response to setting dynamics (Panait and Luke, 2005; Sutton and Barto, 2018).”
BackgroundDistributed scalable multi-robot learning using particle swarm optimization
Pugh, J., & Martinoli, A. (2009) · Swarm Intelligence · doi:10.1007/s11721-009-0030-z · Cited by 38
“Multi-robot learning has been used and explored in various ways; surveys of work (including learning on non-robotic multi-agent systems) can be found in Stone and Veloso (2000), Panait and Luke (2005).”
MethodCM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement LearningPreprint
Yang, J., Nakhaei, A., Isele, D., Fujimura, K., & Zha, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.05188 · Cited by 69
“a global reward) [5, 26, 6, 22], and while one could treat the cooperative multi-goal scenario as a problem with a single joint goal, this coarse approach makes it extremely difficult to isolate the impact of any agent’s action on any”
BackgroundHenrichs, E., Lesch, V., Straesser, M., Kounev, S., & Krupitzer, C. (2022) · Information and Software Technology · doi:10.1016/j.infsof.2022.106940 · Cited by 37
“Convergence for this technique can be shown for many domains, but not for all real-world ap-294 plications [50].”
BackgroundAdaptive data collection protocol using reinforcement learning for VANETs
Soua, A., & Afifi, H. (2013) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2013.6583700 · Cited by 34
“Fortunately, the reinforcement learning techniques [12] can tackle these problems.”
BackgroundKaisers, M. (2012) · Research Publications (Maastricht University) · doi:10.26481/dis.20121217mk · Cited by 34
Self-Optimization module for Scheduling using Case-based Reasoning
Pereira, I. F., & Madureira, A. M. (2012) · Applied Soft Computing · doi:10.1016/j.asoc.2012.02.009 · Cited by 41
Li, J., Zeng, J. J., Su, X., Luo, W. D., & Wang, J. (2012) · International Journal of Distributed Sensor Networks · doi:10.1155/2012/878595 · Cited by 33
“Although for such case the convergence to the optimal point could not be proved rigorously, this multi-agent learning approach has been shown to converge in multiple applications [14].”
BackgroundLearning Complementary Multiagent Behaviors: A Case Study
Kalyanakrishnan, S., & Stone, P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-11876-0_14 · Cited by 33
“In their survey, Panait and Luke [14] divide cooperative multiagent learning into two broad categories: under team”
BackgroundBelievable and Effective AI Agents in Virtual Worlds: Current State and Future Perspectives
Umarov, I., & Mozgovoy, M. (2012) · International Journal of Gaming and Computer-Mediated Simulations · doi:10.4018/jgcms.2012040103 · Cited by 32
“This topic is a subject of numerous studies (Panait & Luke, 2005; Chernova & Veloso, 2007; Ros, Veloso, de Mántaras, Sierra, & Arcos, 2007; Stone, Kaminka, Kraus, & Rosenschein, 2010).”
Novelty-Driven Cooperative Coevolution
Gomes, J., Mariano, P., & Christensen, A. L. (2015) · Evolutionary Computation · doi:10.1162/evco_a_00173 · Cited by 32
“Cooperative coevolutionary algorithms are, however, plagued by a number of issues, among which premature convergence to stable states stands out (Wiegand, 2004; Panait and Luke, 2005a; Popovici et al., 2012).”
BackgroundMethodInfluential
Metadata
- Authors
- Panait, L., & Luke, S.
- Affiliations
- George Mason University (US)
- Corresponding author
- Panait, Liviu
- ORCID
- Luke, Sean
- Venue
- Autonomous Agents and Multi-Agent Systems
- Published
- 2005-11
- Volume
- 11
- Issue
- 3
- Pages
- 387-434
- ISSN
- 1387-2532 (ISSN-L)
- 1573-7454
- OpenAlex
- W2107544712
- Cited by
- 1,237
- References
- 327
- Citations by year
- 2026: 39 · 2025: 42 · 2024: 39 · 2023: 67 · 2022: 48 · 2021: 69 · 2020: 78 · 2019: 80 · 2018: 74 · 2017: 64 · 2016: 58 · 2015: 72 · 2014: 74 · 2013: 89 · 2012: 66
- FWCI
- 32.04
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Autonomous Agents and Multi-Agent Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- cooperative multi-agent learning, multi-agent systems, team learning, concurrent learning, direct communication, indirect communication, task decomposition, scalability, adaptive dynamics, evolutionary computation, game theory, reinforcement learning, agent-based modeling, robotics, complex systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.