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 401–500 of 1,000
Gradient Monitored Reinforcement Learning
Hameed, M. S. A., Chadha, G. S., Schwung, A., & Ding, S. X. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3119853 · Cited by 16
“For the architecture of the robotic multiagent, independent learners with communication enabled between the agents were chosen since it is established that communication between the agents helps in faster convergence [62].”
BackgroundEvolving Team Compositions by Agent Swapping
Lichocki, P., Wischmann, S., Keller, L., & Floreano, D. (2012) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2012.2191292 · Cited by 16
“In contrast to agent recombination [16]–[18], no attempts have been made to quantify the efficiency of agent swapping in the evolution of teams [12].”
BackgroundInfluentialParticipant Selection for Short-term Collaboration in Open Multi-agent systems
Golpayegani, F., Sahaf, Z., Dusparić, I., & Clarke, S. (2017) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2017.11.007 · Cited by 15
Intelligent Adapted e-Learning System based on Deep Reinforcement Learning
Fouki, M. E., Aknin, N., & El-Kadiri, K. E. (2017) · International Conference Computing and Wireless Communication Systems · doi:10.1145/3167486.3167574 · Cited by 13
“In computing, a multi-agent system is a compound system of a set of agents, situated in an environment and interacting according to specific relations [1].”
BackgroundSwarm Q-Learning With Knowledge Sharing Within Environments for Formation Control
Nguyen, T., Nguyen, H. T., Debie, E., Kasmarik, K., Garratt, M., & Abbass, H. A. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489674 · Cited by 13
Intelligent software web agents: A gap analysis
Kirrane, S. (2021) · Journal of Web Semantics · doi:10.1016/j.websem.2021.100659 · Cited by 18
“, [116, 141, 12]) that could serve as the basis for the development of this component.”
BackgroundMulti-criteria expertness based cooperative Q-learning
Pakizeh, E., Palhang, M., & Pedram, M. M. (2012) · Applied Intelligence · doi:10.1007/s10489-012-0392-6 · Cited by 13
Sensing time and power allocation for cognitive radios using distributed Q-learning
van den Biggelaar, O., Dricot, J., Doncker, P. D., & Horlin, F. (2012) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/1687-1499-2012-138 · Cited by 13
Dynamic Spectrum Sharing in Cognitive Radio Networks: A Solution based on Multiagent Systems
Mir, U., Merghem, L., & Gaïti, D. (2010) · Cited by 13
Cooperative Coevolution of Control for a Real Multirobot System
Gomes, J., Duarte, M., Mariano, P., & Christensen, A. L. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45823-6_55 · Cited by 14
Autonomous Context-Based Service Optimization in Mobile Cloud Computing
Nawrocki, P., & Śnieżyński, B. (2017) · Journal of Grid Computing · doi:10.1007/s10723-017-9406-2 · Cited by 15
“It is not a traditional approach because autonomous online learning, usually considered in the context of agent-based systems, is typically realized using reinforcement learning (see surveys [23, 24]).”
BackgroundBuilding Collaboration in Multi-agent Systems Using Reinforcement Learning
Aydın, M. E., & Fellows, R. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-98446-9_19 · Cited by 12
“Researchers are conscious on that solving complex and large problems with distributed approaches remains as a challenging issue due to the fact that there is not a productive method to commonly use for organising distributed intelligence (agents in this case) for a high efficiency [24, 29, 35].”
BackgroundMethodClique-based cooperative multiagent reinforcement learning using factor graphs
Zhang, Z., & Zhao, D. (2014) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2014.7004682 · Cited by 13
“In fact, our method is very similar to hybrid team learning([43]) which has been investigated in genetic programming by Luke([44]).”
BackgroundMethodTraining Time and Team Composition Robustness in Evolved Multi-agent Systems
Thomason, R., Heckendorn, R. B., & Soule, T. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-78671-9_1 · Cited by 13
“Evolutionary algorithms are often used to evolve teams of agents, where the goal is to maximize utility or solve a task, what Panait and Luke call cooperative multi-agent learning [6].”
BackgroundCooperative reinforcement learning in topology-based multi-agent systems
Xiao, D., & Tan, A. (2011) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-011-9183-4 · Cited by 13
“We adopt a hybrid reward scheme [1] in the TD-FALCON BTF algorithm.”
BackgroundMethodSkynet: A Top Deep RL Agent in the Inaugural Pommerman Team CompetitionPreprint
Gao, C., Hernández-Leal, P., Kartal, B., & Taylor, M. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.01360 · Cited by 20
“Similarly, one agent could eliminate both opponents whereas its teammate just camps; both agents would get positive rewards, reinforcing a lazy agent [7].”
BackgroundPang, D., Guo, Y., Cao, J., Zhao, X., & Meng, H. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2024.106778 · Cited by 12
MAS-LSTM: A Multi-Agent LSTM-Based Approach for Scalable Anomaly Detection in IIoT Networks
Qin, Z., Luo, Q., Nong, X., Chen, X., Zhang, H., & Wong, C. U. I. (2025) · Processes · doi:10.3390/pr13030753 · Cited by 20
VeSCA: Vehicular stable cluster-based data aggregation
Uçar, S., Çöleri, S., & Özkasap, Ö. (2014) · International Conference on Connected Vehicles and Expo · doi:10.1109/iccve.2014.7297517 · Cited by 12
“[6], [8], [9], [10], [12], [14], [15], [18] focus on structurefree data aggregation techniques; [6] splits the road into segments and performs segment based data aggregation on periodic beacon messages, [8] models the data aggregation problem as a multi-objective optimization problem and exploits particle swarm optimi…”
MethodAutomatic abstraction controller in reinforcement learning agent via automata
Mousavi, S. S., Ghazanfari, B., Mozayani, N., & Jahed‐Motlagh, M. R. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.08.071 · Cited by 12
Cooperative state estimation of multi-agent systems subject to bounded external disturbances
Yuan, C., & Wu, F. (2018) · International Journal of Systems Science · doi:10.1080/00207721.2018.1482380 · Cited by 12
“…analysis and control design problems for multi-agent systems, such as consensus/synchronisation control (Ren, 2005), formation control (Oh et al., 2015), cooperative intelligent learning (Panait & Luke, 2005), information fusion in networked sensor systems (Olfati-Saber & Shamma, 2005), and so on.”
BackgroundVoting-Based Multiagent Reinforcement Learning for Intelligent IoT
Xu, Y., Deng, Z., Wang, M., Xu, W., So, A. M., & Cui, S. R. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3021017 · Cited by 18
“In the context of Markov games, the study of MARL usually models the MARL as stochastic games, such as cooperative games [31], zero-sum stochastic games [32], [36]–[38], general-sum stochastic games [33], decentralized Q-learning [35], and the recent mean-field MARL [34].”
BackgroundMethodDecentralized Multi-Agent Control of a Manipulator in Continuous Task Learning
Shahid, A. A., Sesin, J. S. V., Pecioski, D., Braghin, F., Piga, D., & Roveda, L. (2021) · Applied Sciences · doi:10.3390/app112110227 · Cited by 13
“[19] provides a survey for cooperative multi-agent learning literature where the work is divided into two categories.”
BackgroundParallel Automatic History Matching Algorithm Using Reinforcement Learning
Alolayan, O. S., Alomar, A. O., & Williams, J. R. (2023) · Energies · doi:10.3390/en16020860 · Cited by 12
Multi-criteria expertness based cooperative method for SARSA and eligibility trace algorithms
Pakizeh, E., Pedram, M. M., & Palhang, M. (2015) · Applied Intelligence · doi:10.1007/s10489-015-0665-y · Cited by 12
“The capability of cooperation in multi-agent systems is critical in achieving better performance and results in higher efficiency and faster learning compared to individual learning, due to more resources of knowledge and information [1].”
BackgroundA Single Population Genetic Programming based Ensemble Learning Approach to Job Shop Scheduling
Park, C. H., Nguyen, S., Zhang, M., & Johnston, M. (2015) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2739482.2764651 · Cited by 12
“Ensemble learning [5] and multi-agent systems [6] have been proposed in the learning, a rule is comprised of multiple smaller constituent rules, and a consensus is reached between the constituent rules to form an output.”
BackgroundTask switching in multirobot learning through indirect encoding
D’Ambrosio, D. B., Lehman, J., Risi, S., & Stanley, K. O. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6094509 · Cited by 12
“is an established evolutionary method for training teams of agents that must work together [10]–[12].”
BackgroundMethodOn a Multi-agent Distributed Asynchronous Intelligence-Sharing and Learning Framework
Jha, S. S., & Nair, S. B. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-48145-5_9 · Cited by 14
“Research in the domain of multi-agent learning [1] has largely bifurcated into two streams - those that use reinforcement learning and the non-conventional evolutionary learning paradigms [36].”
BackgroundAutomatic synthesis of swarm behavioural rules from their atomic components
Samarasinghe, D., Lakshika, E., Barlow, M., & Kasmarik, K. (2018) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3205455.3205546 · Cited by 12
“However, automation of swarm behaviours has achieved limited success with this approach [15] due to the limitations in decomposition of global reward at the emergent level into individual rewards for agents.”
BackgroundAdaptive multiple crossover genetic algorithm to solve workforce scheduling and routing problem
Algethami, H., Martı́nez-Gavara, A., & Landa-Silva, D. (2018) · Journal of Heuristics · doi:10.1007/s10732-018-9385-x · Cited by 12
Review of the progress of communication-based multi-agent reinforcement learning
王, 涵., 俞, 扬., & 姜, 远. (2021) · Scientia Sinica Informationis · doi:10.1360/ssi-2020-0180 · Cited by 12
Q-Strategy: A Bidding Strategy for Market-Based Allocation of Grid Services
Borissov, N., & Wirström, N. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88871-0_52 · Cited by 12
“A wide summary of common learning algorithms and decision rules are presented by [45–47, 37, 15, 48, 49]”
Agent-based modelling of multi-robot systems
Oprea, M. M. (2018) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/444/5/052026 · Cited by 12
“Examples of MAS applications in multi-robot system are presented in [6], [9], [15].”
BackgroundMachine Learning Improves Human-Robot Interaction in Productive Environments: A Review
Zamora-Hernández, M.-A., Marin, E. G. C., García‐Rodríguez, J., Azorín-López, J., & Cazorla, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59147-6_25 · Cited by 12
The analysis and design of concurrent learning algorithms for cooperative multiagent systems
Luke, S., & Panait, L. (2007) · Cited by 13
Self-citationCooperative Multi-agent Reinforcement Learning for Inventory Management
Khirwar, M., Gurumoorthy, K. S., Jain, A. A., & Manchenahally, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43427-3_37 · Cited by 18
Cao, X., Luo, H., Tai, J., Jiang, R., & Wang, G. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110999 · Cited by 11
DVF:Multi-agent Q-learning with difference value factorization
Huang, A., Wang, Y., Sang, J., Wang, X. L., & Wang, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111422 · Cited by 11
Observation, Communication and Intelligence in Agent-Based Systems
Chmait, N., Dowe, D. L., Green, D. G., & Li, Y.-F. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-21365-1_6 · Cited by 13
“The literature on multiagent systems has put forward many studies showing how factors such as communication [7,3,1,9] and observation [4,11,5] influence the performance of multiagent systems.”
BackgroundFRIGHT: A flexible rule-based intelligent ghost team for Ms. Pac-Man
Gagne, D. J., & Congdon, C. B. (2012) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2012.6374166 · Cited by 11
“Pac-Man, there has been extensive work in applying learning techniques to the multi-agent problem; Panait and Luke provide a review of work in cooperative multi-agent learning in [15].”
MethodWestra, J., Dignum, F. P. M., & Dignum, V. (2010) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/itw.2010.5593322 · Cited by 11
“Although many applications with learning agents exist, multi-agent systems with learning agents are usually very unpredictable [15].”
BackgroundEvolution of a Communication Code in Cooperative Tasks
Rawal, A., Rajagopalan, P., Miikkulainen, R. P., & Holekamp, K. E. (2012) · Conference on Artificial Life (ALIFE) · doi:10.7551/978-0-262-31050-5-ch033 · Cited by 11
“In artificial intelligence, the problem of coordination among multiple predator agents during prey capture is hard because of the non-Markovian environment (Panait and Luke, 2005).”
BackgroundAbdulghafor, R. A. A., Turaev, S., Zeki, A. M., & Abubaker, A. (2017) · Journal of Artificial Intelligence and Soft Computing Research · doi:10.1515/jaiscr-2018-0003 · Cited by 14
“A multi-agent system in the most general sense, is defined as a network system of several autonomous agents that are capable of local interactions [30].”
BackgroundCombining Rule Induction and Reinforcement Learning: An Agent-based Vehicle Routing
Śnieżyński, B., Wójcik, W., Gehrke, J. D., & Wojtusiak, J. (2010) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2010.132 · Cited by 11
Evolution of team composition in multi-agent systems
Rubini, J., Heckendorn, R. B., & Soule, T. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1570045 · Cited by 11
“A great deal of research has been devoted to developing training methods for teams of robotic agents, often referred to as “cooperative multi-agent learning” [10].”
BackgroundNamoun, A., Marín, C. A., Germain, B. S., Mehandjiev, N., & Philips, J. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40090-2_16 · Cited by 11
Cooperative Learning in Multiagent Systems from Intermittent Measurements
Leonard, N. E., & Olshevsky, A. (2013) · SIAM Journal on Control and Optimization · doi:10.1109/cdc.2013.6761079 · Cited by 10
Neuroevolution of mobile ad hoc networks
Knoester, D. B., Goldsby, H. J., & McKinley, P. K. (2010) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1830483.1830594 · Cited by 11
A strategy learning model for autonomous agents based on classification
Śnieżyński, B. (2015) · International Journal of Applied Mathematics and Computer Science · doi:10.1515/amcs-2015-0035 · Cited by 11
“The second method of learning often used in agent-based systems or evolutionary computations relies on the processing of many agent generations, improving their performance in subsequent iterations (Panait and Luke, 2005).”
BackgroundMethodINFLUENCE LEARNING FOR MULTI-AGENT SYSTEM BASED ON REINFORCEMENT LEARNING
Kabysh, A., Golovko, V. A., & Lipnickas, A. (2014) · International Journal of Computing · doi:10.47839/ijc.11.1.549 · Cited by 11
“At the same time, Multi-Agent learning (MAL) poses significant theoretical challenges, particularly in understanding how agents can learn and adapt in the presence of other agents that are simultaneously learning and adapting [2,3].”
BackgroundHu, Y., Chen, M., Yang, Z., Chen, M., & Jia, G. (2020) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc48278.2020.9217276 · Cited by 11
“How to integrate distribution of all agents to the global Q-table dynamically is related to game theory [14] and evolutionary computation [15].”
BackgroundLeveraging Organizational Guidance Policies with Learning to Self-Tune Multiagent Systems
Harmon, S. J., DeLoach, S. A., Robby, & Caragea, D. (2008) · IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) · doi:10.1109/saso.2008.46 · Cited by 11
“Many authors have explored applying various learning techniques in a multiagent context [13, 18, 19].”
BackgroundDynamic uplink/downlink configuration using Q-learning in femtocell networks
Wang, Y., & Tao, M. (2014) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccchina.2014.7008242 · Cited by 11
“However, the multi-agent Q-learning algorithm cannot always converge, but it is shown to converge under many cases [14].”
BackgroundNeural Replicator DynamicsPreprint
Hennes, D., Morrill, D., Omidshafiei, S., Munos, R., Pérolat, J., Lanctot, M., Gruslys, A., Lespiau, J.-B., Parmas, P., Duenez-Guzman, E., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00190 · Cited by 33
“In multiagent reinforcement learning (MARL), agents interact in a shared environment and aim to learn policies that maximize their returns [15, 48, 62].”
BackgroundLearning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance
Fang, Y., Tang, Z., Ren, K., Liu, W., Zhao, L., Bian, J., Li, D., Zhang, W., Yu, Y. H., & Liu, T. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599856 · Cited by 30
“Early works [11, 34, 35] design pre-defined communication protocols between agents.”
BackgroundChen, S., Zhang, Z., Yang, Y., & Du, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29681 · Cited by 19
“Cooperative Multi-Agent Reinforcement Learning In a fully cooperative multi-agent task (Panait and Luke 2005), agents need to work independently to achieve a common goal.”
BackgroundJiang, Y., Di, K., Qian, R., Wu, X., Chen, F., Li, P., Fu, X., & Jiang, Y. (2024) · Tsinghua Science & Technology · doi:10.26599/tst.2024.9010013 · Cited by 10
A tournament-based competitive-cooperative multiagent architecture for real parameter optimization
Lotfi, N., & Acan, A. (2015) · Soft Computing · doi:10.1007/s00500-015-1768-4 · Cited by 11
“A general description of agent environments and their categorical properties can be found in Panait and Luke (2005).”
BackgroundInfluentialDistributed Learning for Planning Under Uncertainty Problems with Heterogeneous Teams
Üre, N. K., Chowdhary, G. V., Chen, Y. F., How, J. P., & Vian, J. L. (2013) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-013-9980-x · Cited by 10
“In particular, in the heterogeneous learning setting [16], where the agents are learning different models, sharing model information may actually harm the overall system performance.”
BackgroundSwarms of Metaheuristic Agents: A Model for Collective intelligence
Aydın, M. E., Wu, J., & Zhang, L. (2010) · International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC) · doi:10.1109/3pgcic.2010.49 · Cited by 10
“The-state-ofthe-art of coordinating multi agents via machine learning has been extensively discussed in [20], [11], [10] emphasizing the organizational and architectural issues of multi-agent systems.”
BackgroundSynchronized Cooperative Learning for Coordinating Cognitive Network Management Functions
Mwanje, S. S., Sanneck, H., & Mitschele‐Thiel, A. (2018) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2018.2805349 · Cited by 10
“thus apply MAS approaches for which are four options [4]: 1) Single-Agent System (SAS) decomposition or simply Separation, where functions are scheduled to be inde-”
MethodCooperation Enforcement and Collusion Resistance in Repeated Public Goods Games
Li, K., & Hao, D. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33012085 · Cited by 10
One4All: Manipulate one agent to poison the cooperative multi-agent reinforcement learning
Zheng, H., Li, X., Chen, J., Dong, J., Zhang, Y., & Lin, C. (2022) · Computers & Security · doi:10.1016/j.cose.2022.103005 · Cited by 17
Guiding User Adaptation in Serious Games
Westra, J., Dignum, F. P. M., & Dignum, V. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-18181-8_9 · Cited by 10
Śnieżyński, B., & Dajda, J. (2012) · Journal of Computational Science · doi:10.1016/j.jocs.2012.03.003 · Cited by 10
“Good survey of learning in multi-agent systems working in various domains can be found in [2,3].”
BackgroundBeyond Reinforcement Learning and Local View in Multiagent Systems
Bazzan, A. L. C. (2014) · Künstliche Intell. · doi:10.1007/s13218-014-0312-5 · Cited by 10
“Hierarchical clustering: [29] Clustering: [7, 25, 38, 41, 43]”
MethodGenetic Variation and the Evolution of Consensus in Digital Organisms
Knoester, D. B., Goldsby, H. J., & McKinley, P. K. (2012) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2012.2201725 · Cited by 11
“W ITHIN THE FIELD of evolutionary computation, there is increasing interest in evolving groups of individuals to solve complex problems [1], [2].”
BackgroundMethodTowards computational models of animal cognition, an introduction for computer scientists
Ma, Z. S. (2014) · Cognitive Systems Research · doi:10.1016/j.cogsys.2014.08.001 · Cited by 10
Virtual Field Testing for Performance Evaluation of Cooperative Multiple Robots
Ryu, K., & Furukawa, T. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33515-0_60 · Cited by 10
“The basic principle that unifies MARL techniques is to identify and reward promising cooperative states and actions among a team of agents [9, 10].”
Theoretical advantages of lenient Q-learners
Panait, L., & Tuyls, K. (2007) · Adaptive Agents and Multi-Agents Systems · doi:10.1145/1329125.1329173 · Cited by 10
“Panait et al. (2006) presents evidence on the advantages of such an approach.”
Self-citationOn the Scalability and Dynamic Load-Balancing of Optimistic Gate Level Simulation
Meraji, S., Zhang, W., & Tropper, C. (2010) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2010.2049044 · Cited by 10
“1) Single Agent Versus Multiagent: RL can formulate the dynamic load-balancing of time warp as single agent or multiagent [31] problem.”
BackgroundSaeid, Y., Dola, K. B., Azizi, M. M., & Yusof, M. J. M. (2014) · Environmental Management and Sustainable Development · doi:10.5296/emsd.v4i1.6557 · Cited by 11
“In the artificial intelligence-related literature, this term is used to study the interaction of autonomous agents (see, for example, Panait & Luke, 2005; Durfee, 2001; Wooldridge, 2002).”
MethodCreating Believable and Effective AI Agents for Games and Simulations: Reviews and Case Study
Umarov, I., & Mozgovoy, M. (2014) · Advances in systems analysis, software engineering, and high performance computing book series · doi:10.4018/978-1-4666-6252-0.ch003 · Cited by 16
Allocating training instances to learning agents for team formation
Liemhetcharat, S., & Veloso, M. (2017) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-016-9355-3 · Cited by 14
The emergence of cooperation in the thermodynamic limit
Benjamin, C., & Sarkar, S. (2020) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2020.109762 · Cited by 10
“The problem of many or infinite number of agents collaborating is an outstanding problem not just in game theory but in artificial intelligence too[3].”
BackgroundMahfoudh, H. B., Serugendo, G. D. M., Boulmier, A., & Abdennadher, N. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03424-5_17 · Cited by 10
Toward Computational Motivation for Multi-Agent Systems and Swarms
Khan, M. M., Kasmarik, K., & Barlow, M. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00134 · Cited by 14
“Studies involving multi-agent systems include the communication and behavior (Panait and Luke, 2005) among multiple artificial agents.”
BackgroundMulti-regional Anti-jamming Communication Scheme Based on Transfer Learning and Q Learning
Han, C., & Niu, Y. (2019) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2019.07.001 · Cited by 10
“Because of the independence of neighboring regions, each user independently utilizes the AQLA algorithm to obtain the anti-jamming policy of that particular region, but with Q-value initialization based on the anti-jamming knowledge transferred [30, 31].”
MethodEngineered self-organization for resilient robot self-assembly with minimal surprise
Kaiser, T. K., & Hamann, H. (2019) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2019.103293 · Cited by 12
“Methods of machine learning, such as multi-agent learning [4, 5], seem a reasonable option.”
BackgroundSwarm Robotics Foraging Approaches
Efremov, M. A., & Kholod, I. I. (2020) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/eiconrus49466.2020.9039340 · Cited by 15
“Currently, two classes of machine learning approaches are used that apply to this field: reinforced learning (RL) and evolutionary algorithms (EA) [17].”
BackgroundBourgne, G., Soldano, H., & Amal, E. F. S. (2010) · Frontiers in artificial intelligence and applications · doi:10.3233/978-1-60750-606-5-85 · Cited by 10
“This article deals with the problem of collaborative learning [9] in a multi-agent system (MAS).”
BackgroundMultiagent Based Spectrum Sharing Using Petri Nets
Mir, U., Merghem, L., & Gaïti, D. (2010) · Advances in intelligent and soft computing · doi:10.1007/978-3-642-12433-4_63 · Cited by 10
The Teaching-Box: A universal robot learning framework
Ertel, W., Schneider, M., Cubek, R., & Tokic, M. (2009) · International Conference on Advanced Robotics (ICAR) · Cited by 10
Agent-based Adaptation System for Service-oriented Architectures Using Supervised Learning
Śnieżyński, B. (2014) · Procedia Computer Science · doi:10.1016/j.procs.2014.05.095 · Cited by 11
“In agent domain adaptation and learning are common research topics [19, 22, 32].”
BackgroundA Statistical Property of Multiagent Learning Based on Markov Decision Process
Iwata, K., Ikeda, K., & Sakai, H. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.875990 · Cited by 10
“In this paper, we first show that the AEP is satisfied for empirical sequences in the multiagent case, in which interest has been growing in the field of artificial intelligence [12]–[17].”
BackgroundMalikopoulos, A. A., Papalambros, P. Y., & Assanis, D. N. (2007) · ASME International Mechanical Engineering Congress and Exposition (IMECE) · doi:10.1115/imece2007-41258 · Cited by 12
“Future research should investigate the potential of advancing the POD method to accommodate more than one decision maker in sequential decision-making problems under uncertainty, known as multiagent systems [39].”
MethodNeuro-Evolution for Emergent Specialization in Collective Behavior Systems
Nitschke, G. (2009) · Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam) · Cited by 10
Cognitive Networks: Foundations to Applications
Friend, D. H. (2009) · VTechWorks (Virginia Tech) · Cited by 10
Prompt2Task: Automating UI Tasks on Smartphones from Textual Prompts
Huang, T. Y., Yu, C., Shi, W., Peng, Z., Yang, D. C., Sun, W., & Shi, Y. (2025) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3716132 · Cited by 28
“To meet these challenges, we employ a multi-agent framework [58] for Prompt2Task.”
Gradient Play in Stochastic Games: Stationary Points and Local Geometry
Zhang, R. C., Ren, Z., & Li, N. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.11.031 · Cited by 12
Scalable multi-agent learning algorithms to determine winners in combinatorial double auctions
Hsieh, F.-S., & Liao, C. (2015) · Applied Intelligence · doi:10.1007/s10489-014-0643-9 · Cited by 9
On the evolution of homogeneous two-robot teams: clonal versus aclonal approaches
Tuci, E., & Trianni, V. (2014) · Neural Computing and Applications · doi:10.1007/s00521-014-1594-0 · Cited by 9
“to the fact that the agents of a team share identical controllers, in homogeneous teams there is no need to divvy up among the team members the reward received through their joint actions [18].”
BackgroundIntegrated Agent-based modeling and optimization in complex systems analysis
Humann, J. D., & Madni, A. M. (2014) · Procedia Computer Science · doi:10.1016/j.procs.2014.03.097 · Cited by 9
Sustainable cooperative coevolution with a multi-armed bandit
Rainville, F.-M. D., Sébag, M., Gagné, C., Schoenauer, M., & Laurendeau, D. (2013) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2463372.2463556 · Cited by 9
“Examples of successful applications of cooperative coevolution include ensemble pattern classification [8], multi-agent learning [12], and sensor placement [5], among others.”
BackgroundStochastic Reinforcement Learning
Kuang, N. L., Leung, C. H. C., & Sung, V. W. K. (2018) · IEEE International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) · doi:10.1109/aike.2018.00055 · Cited by 11
“Most of the time, when modeling real-world problems, the environment involved is non-stationary and noisy [1][4][6].”
BackgroundTeka, B., & Dutta, A. (2019) · International Journal of Modelling and Simulation · doi:10.1080/02286203.2019.1670034 · Cited by 9
Using Human-Agent Teams to Purposefully Design Multi-Agent Systems
Flathmann, C., McNeese, N. J., & Canonico, L. B. (2019) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181319631238 · Cited by 10
“A cooperative learning approach would also be used to aid in the training of worker agents by allowing agents with similar problem sets to receive similar training (Panait and Luke, 2005).”
MethodFlow-Based Reinforcement Learning
Samarasinghe, D., Barlow, M., & Lakshika, E. (2022) · IEEE Access · doi:10.1109/access.2022.3209260 · Cited by 9
“This is primarily caused by the increased complexity of operation associated with changes in the environment [11], [12], [13].”
BackgroundAn Architecture for Intelligent Agent-Based Digital Twin for Cyber-Physical Systems
Marah, H., & Challenger, M. (2023) · Springer eBooks · doi:10.1007/978-981-99-0252-1_3 · Cited by 15
Market-Inspired Approach to Collaborative Learning
Tožička, J., Jakob, M., & Pěchouček, M. (2006) · Lecture notes in computer science · doi:10.1007/11839354_16 · Cited by 9
“Panait and Luke [3] present an exhaustive review of cooperative methods for multi-agent learning.”
Background
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.