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 501–600 of 1,000
Enhancing Nash Q-learning and Team Q-learning mechanisms by using bottlenecks
Ghazanfari, B., & Mozayani, N. (2014) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/ifs-130945 · Cited by 9
“Eachagentadaptationmakesitspolicies , which they are going to learn, are no more This is a contravention of many of theoretical RL methods [4, 16, 24, 27, 32]. is a straightforward proof of convergence to reward is used as the credit assignment strategy details see [27]).”
InfluentialZoethout, K., Jager, W., & Molleman, E. (2007) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-007-9022-9 · Cited by 10
“This approach originates from complexity theory and employs multi-agent simulation as a methodology to describe higher order developmental and adaptation processes in terms of local interactions [2,7,12,18], see also [4,8].”
MethodCooperative Q‐learning techniques for distributed online power allocation in femtocell networks
Saad, H., Mohamed, A. M. S., & ElBatt, T. (2014) · Wireless Communications and Mobile Computing · doi:10.1002/wcm.2470 · Cited by 9
“Despite this limitation, applying the single-agent update rule directly in the multi-agent case, where each agent assumes other agents to be part of the environment, has found a significant number of applications, mainly because of its simplicity [6,18].”
MethodCombining coordination mechanisms to improve performance in multi-robot teams
Nasroullahi, E. M., & Tumer, K. (2012) · Artificial Intelligence Research · doi:10.5430/air.v1n2p1 · Cited by 10
“Coordinating a team of agents such that they collectively achieve a common goal is a complex problem within the field of multiagent systems [15].”
BackgroundMachine Learning Algorithms for Multi-Agent Systems
Khalil, K. M., Abdel-Aziz, M. H., Nazmy, T. T., & Salem, A. M. (2015) · International Conference on Intelligent Information Processing, Security and Advanced Communication (IPAC) · doi:10.1145/2816839.2816925 · Cited by 11
“This approach is to consider the problem as a whole, with the aim of finding optimal joint actions [32].”
BackgroundDesigning minimal effective normative systems with the help of lightweight formal methods
Hao, J., Kang, E., Sun, J., & Jackson, D. N. (2016) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/2950290.2950307 · Cited by 10
“is also applicable to other similar domains such as prey-predator problem [32] or other multi-agent coordination problems [26].”
Solving Multi-agent Control Problems Using Particle Swarm Optimization
Mazurowski, M. A., & Zurada, J. M. (2007) · IEEE Swarm Intelligence Symposium · doi:10.1109/sis.2007.368033 · Cited by 9
“Decision making in multi-agent systems has been gaining increasing attention over the past years [1].”
BackgroundMellah, Y., Rhouati, A., Ettifouri, E. H., Bouchentouf, T., & Belkasmi, M. G. (2021) · Journal of Computer Science · doi:10.3844/jcssp.2021.480.489 · Cited by 9
“…both understanding the meaning of Natural Language (NL) sentences and mapping them to formal meaning representations (Zelle and Mooney, 1996; Panait and Luke, 2005; Clarke et al ., 2010; Liang et al ., 2011) often to machine-executable programs, for a range of tasks such as…”
BackgroundHuang, S., Wang, T., Tang, Y., Hu, Y., Gu, X., & Zhou, D. (2023) · Aerospace · doi:10.3390/aerospace10020096 · Cited by 8
Artificial intelligence (AI) enhanced nanomotors and active matter
Cichos, F., Muíños-Landín, S., & Pradip, R. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-85796-3.00005-6 · Cited by 8
Reinforcement learning architecture for cyber–physical–social AI: state-of-the-art and perspectives
Li, X., Wang, P., Jin, X., Jiang, Q., Zhou, W., & Yao, S. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10450-2 · Cited by 13
“There are some several general surveys (Kaelbling et al. 1996; Gao et al. 2004; Gosavi 2009) and specific (Kober et al. 2013; Busoniu et al. 2008; Panait and Luke 2005; Matignon et al. 2012; Garcıa and Fernández 2015; Taylor and Stone 2009; Luong et al. 2019; Grondman et al. 2012; Nguyen et al.…”
BackgroundFeng, Z., He, Z., Lin, X., He, W., Guo, L., Zhang, Z., Wei, F., Li, Z., Dawoud, S. M., & Khalid, M. S. (2024) · Energy Reports · doi:10.1016/j.egyr.2024.05.034 · Cited by 8
Power allocation in cognitive radio networks using distributed machine learning
van den Biggelaar, O., Dricot, J., Doncker, P. D., & Horlin, F. (2012) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc.2012.6362898 · Cited by 8
“cost or reward) is provided after an action is performed in the environment [6].”
BackgroundPlatform for distributed execution of agents for trusted data collection
Gatial, E., Balogh, Z., & Hluchý, L. (2010) · Procedia Computer Science · doi:10.1016/j.procs.2010.04.226 · Cited by 8
Runtime efficiency of adaptive mobile software agents in pervasive computing environments
Gunasekera, K., Krishnaswamy, S. P., Loke, S. W., & Zaslavsky, A. (2009) · International Conference on Pervasive Services · doi:10.1145/1568199.1568218 · Cited by 8
“Categories and Subject Descriptors I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence; C.2.4 [Distributed Systems]: Distributed Applications General Terms Algorithms, Performance, Experimentation Keywords Pervasive computing, mobile agents, adaptive software, cost model”
BackgroundInfluentialTeam Search Tactics Through Multi-Agent HyperNEAT
Reeder, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23108-2_7 · Cited by 8
“It is interesting because of the joint behaviors and the complexities arising from the interactions of agents with some degree of autonomy [13].”
BackgroundCyclic error correction based Q-learning for mobile robots navigation
Tang, R., & Yuan, H. (2017) · International Journal of Control Automation and Systems · doi:10.1007/s12555-015-0392-5 · Cited by 8
Time-Dependence in Multi-Agent MDP Applied to Gate Assignment Problem
Aoun, O., & Afia, A. E. (2018) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2018.090247 · Cited by 8
“MMDP can be viewed as a generalization of MDP with a single agent; Or, but also a special case of Markov games [29] where the payoff function is identical for all agents.”
BackgroundMachine Learning in Multi-Agent Systems using Associative Arrays
Spychalski, P., & Arendt, R. (2018) · Parallel Computing · doi:10.1016/j.parco.2018.03.006 · Cited by 8
A parallel refined probabilistic approach for QoS-aware service composition
Wang, H., Peng, S., & Yu, Q. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.03.053 · Cited by 8
Avoiding collaborative paradox in multi‐agent reinforcement learning
Kim, H., Kim, S., Lee, D., & Jang, I. (2021) · ETRI Journal · doi:10.4218/etrij.2021-0010 · Cited by 8
“In such collaborative settings of game environments, recent approaches, such as multi-agent reinforcement learning (MARL) [4], AlphaStar [5], and Dota [6], have shown great successes than cooperative multi-agent systems (MAS) [7].”
BackgroundAgent Strategy Generation by Rule Induction
Śnieżyński, B. (2014) · Cited by 8
Synchronous vs. Asynchronous Cooperative Approach to Solving the Vehicle Routing Problem
Barbucha, D. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-16693-8_42 · Cited by 8
Exploiting Structure in Cooperative Bayesian Games
Oliehoek, F. A., Whiteson, S., & Spaan, M. T. J. (2012) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.1210.4886 · Cited by 8
“tiagent systems are an essential tool, not only for tackling inherently distributed problems, but also for decomposing problems too complex to be tackled by a single agent (Huhns, 1987; Sycara, 1998; Panait and Luke, 2005; Vlassis, 2007; Bu¸soniu et al., 2008). However, to make such systems effective, the constituent a…”
BackgroundBessis, N., Asimakopoulou, E., Aydın, M. E., & Xhafa, F. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-20344-2_19 · Cited by 8
“Tackling this problem universally remains a challenging issue despite of many approaches proposed with being domain-specific [ 41 ; 51; 36].”
BackgroundTuci, E., Mitavskiy, B., & Francesca, G. (2013) · European Conference on Artificial Life · doi:10.7551/978-0-262-31709-2-ch055 · Cited by 10
“…groups tend to imply a smaller search space than heterogeneous groups, and contrary to the latter they are not affected by the credit-assignment problem (i.e., the problem of divvying up among the team members the reward received through their joint actions, (see Panait and Luke, 2005)).”
BackgroundNaeini, A. T., & Ghaziasgar, M. (2009) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2009.5346622 · Cited by 8
“It is a common domain used in Distributed Artificial Intelligence (DAI) research to evaluate techniques for developing cooperation strategies [11].”
BackgroundVidhate, D. A., & Kulkarni, P. A. (2017) · International Journal of Information Technology · doi:10.1007/s41870-017-0079-7 · Cited by 8
“Resultant Q table is found out that is used as its new Q table [15, 16].”
MethodLearned Search Parameters For Cooperating Vehicles using Gaussian Process Regressions
Moon, B. G., & Peterson, C. K. (2018) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas.2018.8453323 · Cited by 8
“edu Reinforcement learning has been introduced as an aspect to minimize the search area coverage rate and has been been examined in [12], [13].”
BackgroundAgent-based cooperative animation for box-manipulation using reinforcement learning
Yang, H.-Y., & Wong, S. (2019) · Proceedings of the ACM on Computer Graphics and Interactive Techniques · doi:10.1145/3320283 · Cited by 8
“Extensive studies have been conducted on studying collective and cooperative behaviors in robotics [Panait and Luke 2005; Rohmer et al. 2013; Tuci et al. 2018] and computer animation [Guo et al. 2017; Xiang et al. 2018].”
Tuning Meta-Heuristics Using Multi-agent Learning in a Scheduling System
Pereira, I. F., Madureira, A. M., Oliveira, P. M., & Abraham, A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-45318-2_8 · Cited by 8
“Panait and Luke [32] have focused machine learning application to problems related with MAS.”
BackgroundInfluentialKemmerich, T., & Büning, H. K. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28499-1_3 · Cited by 8
Performance of heterogeneous robot teams with personality adjusted learning
Recchia, T., Chung, J. H., & POCHIRAJU, K. V. (2013) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2013.10.003 · Cited by 8
Agent Strategy Generation by Rule Induction in Predator-Prey Problem
Śnieżyński, B. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-01973-9_99 · Cited by 8
“Good survey of learning in multi-agent systems can be found in [1] and [2].”
BackgroundImproving Performance and Cooperation in Multi-Agent Systems
Soule, T., & Heckendorn, R. B. (2007) · Springer eBooks · doi:10.1007/978-0-387-76308-8_13 · Cited by 8
Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement LearningPreprint
Celli, A., Ciccone, M., Bongo, R., & Gatti, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07712 · Cited by 20
“Most of them are based on heuristics encouraging agents’ policies coordination [4, 6, 32, 33, 37, 38, 48].”
BackgroundAI-Assisted Dynamic Frame Structure With Intelligent Puncturing Schemes for 5G Networks
Abedi, M. R., Javan, M. R., Pourghasemian, M., Mokari, N., & Jorswieck, E. A. (2023) · IEEE Access · doi:10.1109/access.2023.3323931 · Cited by 11
“However, due to the changing policies of other agents, the environment is not fully observable to the agents [51].”
BackgroundKAVE: A Knowledge-Based Multi-Agent System for Web Vulnerability Detection
Ramires, R., Respício, A., & Medeiros, I. (2024) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws62655.2024.00070 · Cited by 7
“A MAS [25], [26] consists of multiple autonomous agents interacting or working with their fellow agents and the surrounding environment.”
BackgroundQ-CP: Learning Action Values for Cooperative Planning
Riccio, F., Capobianco, R., & Nardi, D. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8460180 · Cited by 7
Wei, Y., Gong, Y., Li, Q., Song, M., & Wang, X. (2020) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2020.010048 · Cited by 7
“…in the MARL system, the convergence can be proved by approximating other agents as environment and applying Bellman’s criterion, although the proof does not hold as strictly as it does in single agent scenario it has been shown to correctly converge in many applications [Panait and Luke (2005)].”
MethodInfluentialCooperative Multi-Agent Deep Reinforcement Learning with Counterfactual Reward
Shao, K., Zhu, Y., Tang, Z., & Zhao, D. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207169 · Cited by 8
“Through mapping the joint space to multiple separated subspaces, concurrent learning can reduce the dimension of search space [14].”
BackgroundTowards designing a generic and comprehensive deep reinforcement learning framework
Nguyen, N. D., Nguyen, T. T., Pham, N. T., Nguyen, V., Nguyen, D. T., Nguyen, T. T., Lim, C. P., Johnstone, M., Bhatti, A., Creighton, D., et al. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03550-z · Cited by 9
Mutual Learning Algorithm for Kidney Cyst, Kidney Tumor and Kidney Stone Diagnosis
Chowdhury, S. T., Mukhopadhyay, S., & Narendra, K. S. (2023) · Annals of Computer Science and Information Systems · doi:10.15439/2023f378 · Cited by 9
“Panait and Luke [41] provide an overview of this well-established field, emphasizing inter-agent communication, task decomposition, and scalability in multi-agent systems.”
BackgroundSmart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Cao, Z., Wang, Z., Xie, S., Liu, A., & Fan, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01713 · Cited by 23
Training Multiagent Systems by Q‐Learning: Approaches and Empirical Results
López-Guede, J. M., Fernandez‐Gauna, B., Graña, M., & Zulueta, E. (2014) · Computational Intelligence · doi:10.1111/coin.12035 · Cited by 7
“This kind of learning systems are known as team learning (Panait and Luke 2005) and are not scalable to big robot teams because the size needed to store the Q-table grows exponentially with the number of agents, even if we consider that the state space does not grow, because the action–state space…”
BackgroundA Hybrid Cooperative Behavior Learning Method for a Rule-Based Shout-Ahead Architecture
Paskaradevan, S., & Denzinger, J. (2012) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2012.33 · Cited by 7
“…Intelligence, Cooperative Systems, Learning Systems I. INTRODUCTION Communication is an important part of many of the cooperation concepts for agents: be it selected good results of an agent that boost the solution state of another agent (see [7]), be it descriptions of…”
BackgroundDistributed Intrusion Detection System Using P2P Agent Mining Scheme
Oriola, O., Adeyemo, A. B., & Robert, A. B. C. (2012) · Cited by 7
Model-assisted approaches for relational reinforcement learning
Croonenborghs, T., Ramon, J., Blockeel, H., & Bruynooghe, M. (2007) · Lirias · Cited by 7
Grammar-based cooperative learning for evolving collective behaviours in multi-agent systems
Samarasinghe, D., Barlow, M., Lakshika, E., & Kasmarik, K. (2021) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2021.101017 · Cited by 10
Smooth Q-Learning: An Algorithm for Independent Learners in Stochastic Cooperative Markov Games
Amhraoui, E., & Masrour, T. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-01917-z · Cited by 8
“Many MARL methods have been proposed for solving fully cooperativeMarkov games.”
BackgroundInfluentialUtilization of a Cooperative Multiagent System in the Context of Cognitive Radio Networks
Mir, U., Merghem, L., & Gaïti, D. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-05006-0_8 · Cited by 7
Learning with Whom to Communicate Using Relational Reinforcement Learning
Ponsen, M., Croonenborghs, T., Tuyls, K., Ramon, J., Driessens, K., van den Herik, H. J., & Postma, E. O. (2010) · Studies in computational intelligence · doi:10.1007/978-3-642-11688-9_2 · Cited by 7
“high reward for the system and high individual rewards for the different agents is still a difficult problem, see, e.g., [9, 17 , 18, 26].”
BackgroundMulti-agent cooperation by reinforcement learning with teammate modeling and reward allotment
Zhou, P., & Shen, H. (2011) · International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) · doi:10.1109/fskd.2011.6019729 · Cited by 7
“One of the key problems in such systems is the problem of coordination: how to ensure that the individual decisions of the agents result in jointly optimal decisions for the group [1].”
BackgroundAccelerated learning in machine learning-based resource allocation methods for Heterogenous Networks
Tefft, J. R., & Kirsch, N. J. (2013) · IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) · doi:10.1109/idaacs.2013.6662729 · Cited by 7
“It has been shown that the independent, multi-agent QL approach converges appropriately in many cases [16].”
BackgroundCoordination of cooperation policies in a peer-to-peer system using swarm-based RL
Vakili, G., & Khorsandi, S. (2011) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2011.11.004 · Cited by 7
Managing Femto to Macro Interference without X2 Interface Support through POMDP
Galindo‐Serrano, A., & Giupponi, L. (2012) · Mobile Networks and Applications · doi:10.1007/s11036-012-0394-y · Cited by 7
“Convergence to an equilibrium for distributed Q-Learning cannot be proven, to the best of the author’s knowledge, however this algorithm has been shown to correctly behave in multiple applications for multiagent systems [36].”
BackgroundImproving testing of multi-unit computer players for unwanted behavior using coordination macros
Atalla, M., & Denzinger, J. (2009) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2009.5286455 · Cited by 7
Application of multi-agent Markov decision processes to gate assignment problem
Aoun, O., & Afia, A. E. (2014) · IEEE Congress on Information Science and Technology (CiSt) · doi:10.1109/cist.2014.7016618 · Cited by 7
Emergence of Conventions for Efficiently Resolving Conflicts in Complex Networks
Sugawara, T. (2014) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2014.171 · Cited by 7
“However, a number of studies have attempted to evolve norms though social interactions using reinforcement learning, although unlike our work, most of them have assumed games between two fixed agents [12].”
BackgroundPlanning against fictitious players in repeated normal form games
de Cote, E. M., & Jennings, N. R. (2010) · doi:10.5555/1838206.1838351 · Cited by 7
Ferrauto, T., Parisi, D., Stefano, G. D., & Baldassarre, G. (2013) · Artificial Life · doi:10.1162/artl_a_00106 · Cited by 7
“(c) Learned specialization: The robots develop different behaviors and roles by suitably updating the connection weights of their controllers on the basis of learning algorithms and experience (see the reviews [55, 56]; these processes might also involve the dynamic update of simple but critical parameters, such as a…”
BackgroundSolving decentralized multi-agent control problems with genetic algorithms
Mazurowski, M. A., & Żurada, J. M. (2007) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2007.4424583 · Cited by 7
“Other examples are air traffic control, electricity distribution management and distributed medical care [1].”
BackgroundCollaborative Concept Learning: Non Individualistic vs Individualistic Agents
Bourgne, G., Bouthinon, D., Seghrouchni, A. E. F., & Soldano, H. (2009) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2009.73 · Cited by 7
“This article deals with the problem of collaborative concept learning in a multi-agent system (see [8] for a recent review).”
BackgroundLiberatore, F., Mora, A. M., Castillo, P. Á., & Merelo, J. J. (2015) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2015.2425795 · Cited by 7
Action Markets in Deep Multi-Agent Reinforcement Learning
Schmid, K., Belzner, L., Gabor, T., & Phan, T. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01421-6_24 · Cited by 8
Ma, C., & Wu, W. L. (2018) · Systems Science & Control Engineering · doi:10.1080/21642583.2018.1547991 · Cited by 7
“This is due to their distinct advantages compared with a traditional single system, which includes high robustness, high reliability, and high efficiency with relatively low cost (Oh, Park, & Ahn, 2015; Panait & Luke, 2005; Van der Hoek & Wooldridge, 2008; Yuan, Wang, Zhang, & Dong, 2018).”
BackgroundTowards Setplays Learning in a Multiagent Robotic Soccer Team
Simões, M. A. C., & Nogueira, T. M. (2018) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars/sbr/wre.2018.00058 · Cited by 7
“We usually can find more researches using reinforcement learning or stochastic optimization methods [21].”
MethodLocal Wealth Redistribution Promotes Cooperation in Multiagent Systems
Pinheiro, F. L., & Santos, F. P. (2018) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/hcsq3483 · Cited by 9
Chung, J. J., Miklić, D., Sabattini, L., Tumer, K., & Siegwart, R. (2020) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-020-09442-1 · Cited by 8
Research directions for Aggregate Computing with Machine Learning
Aguzzi, G. (2021) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) · doi:10.1109/acsos-c52956.2021.00078 · Cited by 8
An Agent Framework for High Performance Simulations over Multi-core Clusters
Cicirelli, F., & Nigro, L. (2013) · Communications in computer and information science · doi:10.1007/978-3-642-45037-2_5 · Cited by 7
Towards Concurrent Q-Learning on Linked Multi-Component Robotic Systems
Fernandez‐Gauna, B., López-Guede, J. M., & Graña, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21222-2_56 · Cited by 7
“To deal with this problem in the L-MCRS control learning, we explore the concurrent learning [ 10 ] which uses simultaneously multiple RL modules assigning each of them a subtask to carry out.”
MethodClosed Loop Optimal Adaptive Traffic Signal and Ramp Control: A Case Study on Downtown Toronto
El-Tantawy, S., Rezaee, K., & Abdulhai, B. (2015) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2015.387 · Cited by 7
Codynamic fitness landscapes of coevolutionary minimal substrates
Richter, H. (2014) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2014.6900272 · Cited by 8
“The advantages of coevolutionary designs are particularly seen for solving competitive problems such as in games [6], [18], or cooperative tasks that require the coordination of several agents such as in some problems related to evolutionary robotics [7], [11], or for situations where the fitness function cannot be de…”
BackgroundMatignon, L., Laurent, G. J., & Fort-Piat, N. L. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5353902 · Cited by 7
Design of Multi-Behavior Agents for Supply Chain Planning: An Application to the Lumber Industry
Forget, P., D’Amours, S., Frayret, J., & Gaudreault, J. (2008) · doi:10.5772/5359 · Cited by 7
“Panait (Panait & Luke, 2005) presents a complete review on this topic, including team learning and concurrent learning.”
BackgroundConcurrent Modular Q-Learning with Local Rewards on Linked Multi-Component Robotic Systems
Fernandez‐Gauna, B., López-Guede, J. M., & Graña, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-21344-1_16 · Cited by 7
“To deal with this problem in the L-MCRS control learning, we explore the concurrent learning approach [ 10 ] which uses simultaneously multiple RL modules assigning each of them a sub-task to carry out.”
MethodCooperative Solution to the Vehicle Routing Problem
Barbucha, D. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13541-5_19 · Cited by 7
“By emphasizing joint behavior of agents and interaction between them to cooperatively solve the tasks or to maximize utility, an important subclass of MAS can be distinguished - cooperative multi-agent systems (CMAS) [7].”
BackgroundReinforcement Learning in an Environment Synthetically Augmented with Digital Pheromones
Barbosa, S. E., & Petty, M. D. (2014) · Advances in Artificial Intelligence · doi:10.1155/2014/932485 · Cited by 7
“The 30-minute response is a stated goal of coalition naval forces [25–57].”
BackgroundEffects of social learning and team familiarity on team performance
Singh, V., Dong, A., & Gero, J. S. (2009) · Spring Simulation Multiconference · doi:10.5555/1639809.1639816 · Cited by 6
Obstacle avoidance of multi mobile robots based on behavior decomposition reinforcement learning
Zu, L., Yang, P., Chen, L., Zhang, X., & Tian, Y. (2007) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2007.4522303 · Cited by 7
“For all kinds of methods, reinforcement learning is paid extensively attention [3-6].”
MethodValue methods for efficiently solving stochastic games of complete and incomplete information
Dermed, M., & Charles, L. (2013) · SMARTech Repository (Georgia Institute of Technology) · Cited by 7
Asher, D. E., Barton, S. L., & Zaroukian, E. G. (2018) · EasyChair preprint · doi:10.29007/dlq7 · Cited by 8
Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic RegulatorPreprint
Luo, Y., Yang, Z., Wang, Z., & Kolar, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.06875 · Cited by 13
“Mean-field MARL problem in a collaborative setting, known as team games (Tan, 1993; Panait and Luke, 2005; Wang and Sandholm, 2003; Claus and Boutilier, 1998), can be regarded as a centralized mean-field control problem (Huang et al., 2012; Carmona et al., 2013; Fornasier and Solombrino, 2014) with…”
BackgroundBee-inspired distributed optimization
Lemmens, N. (2011) · Research Publications (Maastricht University) · doi:10.26481/dis.20111110nl · Cited by 78
Ghaitaranpour, A., Koocheki, A., & Mohebbi, M. (2024) · Current Research in Food Science · doi:10.1016/j.crfs.2024.100751 · Cited by 6
“It is based on the interactions among patches and agents (Bonabeau, 2002; Panait and Luke, 2005).”
BackgroundWu, Y., Wen, Y., Wu, Y., Li, Y., Zheng, X., & Chen, L. (2024) · Sustainability · doi:10.3390/su16146199 · Cited by 6
Learning in public goods games: the effects of uncertainty and communication on cooperation
Orzan, N., Acar, E., Grossi, D., & Rădulescu, R. (2025) · Neural Computing and Applications · doi:10.1007/s00521-024-10530-6 · Cited by 9
“A substantial body of the literature already exists on the emergence of cooperation among artificial agents [12, 48, 49].”
Dirichlet-Multinomial Counterfactual Rewards for Heterogeneous Multiagent Systems
Dixit, G., Zerbel, N., & Tumer, K. (2019) · International Symposium on Multi-Robot and Multi-Agent Systems (MRS) · doi:10.1109/mrs.2019.8901077 · Cited by 6
Iantovics, L. B., Iakovidis, D. K., & Nechita, E. (2019) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.191101.001 · Cited by 6
Run-and-tumble chemotaxis using reinforcement learning
Pramanik, R., Mishra, S., & Chatterjee, S. (2025) · Physical review. E · doi:10.1103/physreve.111.014106 · Cited by 12
Kim, S., Yu, Y., & Seo, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-97498-y · Cited by 15
Femtocell Systems with Self Organization Capabilities
Galindo‐Serrano, A., & Giupponi, L. (2011) · HAL · Cited by 6
Parallel Simulation of Multi-agent Systems Using Terracotta
Cicirelli, F., Furfaro, A., Giordano, A., & Nigro, L. (2010) · International Symposium on Distributed Simulation and Real Time Applications (DS-RT) · doi:10.1109/ds-rt.2010.34 · Cited by 6
“As a case study, a complex multi-agent system based on predator-prey model [7], [8] was developed and simulated.”
MethodRethinking NPC intelligence: a new reputation system
Mooney, J., & Allbeck, J. M. (2014) · Motion in Games · doi:10.1145/2668084.2668091 · Cited by 9
Applying hybrid learning approach to RoboCup's strategy
Kuo, J.-Y., Huang, F.-C., Ma, S., & Fanjiang, Y. (2013) · Journal of Systems and Software · doi:10.1016/j.jss.2013.03.031 · Cited by 6
STIGMERGIC LANDMARK OPTIMIZATION
Lemmens, N., & Tuyls, K. (2012) · Advances in Complex Systems · doi:10.1142/s0219525911500251 · Cited by 9
“These are typical performance measures from the MAS literature [46].”
BackgroundEvolving Dyadic Strategies for a Cooperative Physical Task
Sheybani, S., Izquierdo, E. J., & Roth, E. (2020) · IEEE Haptics Symposium · doi:10.1109/haptics45997.2020.ras.hap20.26.5d3bec79 · Cited by 6
“Our goal is not to design an optimal strategy for role delegation, but rather to discover a variety of feasible strategies [8], [9], as one might expect to find in a sample population of human subjects.”
BackgroundHu, R. Q., & Kwasinski, A. (2020) · European Conference on Power Electronics and Applications · doi:10.23919/epe20ecceeurope43536.2020.9215640 · Cited by 6
“However, these features are not always ensured in a multi-agent environment in which the agents could sometimes end up being locked in limited cycles or local optimums [24], [25].”
BackgroundUsing genetic algorithms to limit the optimism in Time Warp
Wang, J., & Tropper, C. (2009) · Winter Simulation Conference · doi:10.1109/wsc.2009.5429634 · Cited by 6
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.