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 201–300 of 1,000
Mosavi, A. H., & Várkonyi-Kóczy, A. R. (2017) · International Journal of Computer Applications · doi:10.5120/ijca2017911661 · Cited by 47
Li, M., & Deng, F. (2021) · ISA Transactions · doi:10.1016/j.isatra.2021.01.034 · Cited by 32
Agent Collaborative Target Localization and Classification in Wireless Sensor Networks
Wang, X., Bi, D., Ding, L., & Wang, S. (2007) · Sensors · doi:10.3390/s7081359 · Cited by 32
“A multi-agent system is one where there is more than one agent, and where the agents interact with one another [12].”
BackgroundInfluentialTowards a living earth simulator
Paolucci, M., Kossmann, D., Conte, R., Lukowicz, P., Argyrakis, P., BLANDFORD, A. E., Bonelli, G., Anderson, S., de Freitas, S., Edmonds, B., et al. (2012) · The European Physical Journal Special Topics · doi:10.1140/epjst/e2012-01689-8 · Cited by 33
Incremental Clustering and Expansion for Faster Optimal Planning in Decentralized POMDPs
Oliehoek, F. A., Spaan, M. T. J., Amato, C., & Whiteson, S. (2012) · DSpace@MIT (Massachusetts Institute of Technology) · doi:10.1613/jair.3788 · Cited by 32
Yang, B., & Monterola, C. P. (2016) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2016.10.004 · Cited by 31
“ns, velocities as well as their intentions to a central management system; such a central system sends out instructions to each of these vehicles, based on those information and an optimized algorithm[24, 25]. In general such intersection control is vastly superior as compared to the signalized intersection control; o…”
BackgroundCooperative Intelligence - A Humane Perspective
Sendhoff, B., & Wersing, H. (2020) · IEEE International Conference on Human-Machine Systems (ICHMS) · doi:10.1109/ichms49158.2020.9209387 · Cited by 43
“and machines in a smart way has received less attention in the research community compared to cooperation between intelligent agents [15] or supervisory control in automation [16], which primarily aims at the guidance of the machine.”
BackgroundAgent learning in the multi-agent contracting system [MACS]
Rubenstein‐Montano, B., Yoon, V., Drummey, K. W., & Liebowitz, J. (2008) · Decision Support Systems · doi:10.1016/j.dss.2007.12.013 · Cited by 31
A framework for agent-based distributed machine learning and data mining
Tožička, J., Rovatsos, M., & Pěchouček, M. (2007) · Adaptive Agents and Multi-Agents Systems · doi:10.1145/1329125.1329243 · Cited by 31
“The difference between this kind of collaborative agentbased learning systems [16] and our own framework is that these approaches assume a joint learning goal that is pursued collaboratively by all agents.”
BackgroundPark, C. H., Mei, Y., Nguyen, S., Chen, G., Johnston, M., & Zhang, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-30668-1_8 · Cited by 31
“A survey of CCEA techniques is provided by Panait and Luke [17].”
MethodNiazi, M. A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.02357 · Cited by 37
“have either few agents with a focus on certain aspects only, or else do not implement a whole lot of complex behaviors[94], [95].”
BackgroundMethodInfluentialEffective Sentiment-relevant Word Selection for Multi-modal Sentiment Analysis in Spoken Language
Zhang, D., Li, S., Zhu, Q., & Zhou, G. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350987 · Cited by 34
“In multi-agent reinforcement learning (MARL) problems [1, 14, 22, 26], there are a group of autonomous, interacting agents sharing a common environment.”
BackgroundA Survey of Adaptive Multi-Agent Networks and Their Applications in Smart Cities
Nezamoddini, N., & Gholami, A. (2022) · Smart Cities · doi:10.3390/smartcities5010019 · Cited by 52
“As a result of this learning, it may entail homogeneous team learning with one policy for all agents or heterogeneous learning with a unique behavior for each individual agent [187].”
BackgroundKumar, V., Morse, A. S., & Leonard, N. (2005) · Lecture notes in control and information sciences · doi:10.1007/b99788 · Cited by 30
Towards incremental social learning in optimization and multiagent systems
de, M. A. M., & Stützle, T. (2008) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/1388969.1389004 · Cited by 31
Feudal Multi-Agent Hierarchies for Cooperative Reinforcement LearningPreprint
Ahilan, S., & Dayan, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08492 · Cited by 108
“We focused on the cooperative setting [24]; however, unlike the fully-cooperative setting, in which all agents optimise a shared reward function [2] our approach introduces a diversity of rewards, which can help with credit-assignment [4, 35] but also introduces elements of competition.”
BackgroundWang, L., Wang, Z., Gumma, K., Turner, A., & Ratchev, S. M. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02229-7 · Cited by 29
“In a multi-agent system, the agents should have the following three crucial characteristics (Wooldridge, 2009; Panait & Luke, 2005), i.e., autonomy, local views, and decentralisation.”
Reinforcement learning in local energy markets
Bose, S., Kremers, E., Mengelkamp, E., Eberbach, J., & Weinhardt, C. (2021) · Energy Informatics · doi:10.1186/s42162-021-00141-z · Cited by 34
A decentralised multi-agent system for rail freight traffic management
Bretas, A. M. C., Mendes, A. S., Jackson, M., Clement, R., Sanhueza, C., & Chalup, S. K. (2021) · Annals of Operations Research · doi:10.1007/s10479-021-04178-x · Cited by 32
Avoiding convergence in cooperative coevolution with novelty search
Gomes, J., Mariano, P., & Christensen, A. L. (2014) · Repositório do ISCTE-IUL · doi:10.5555/2615731.2617428 · Cited by 29
Nawrocki, P., & Śnieżyński, B. (2017) · Journal of Network and Systems Management · doi:10.1007/s10922-017-9405-4 · Cited by 31
“Valuable studies in this area are [45, 46].”
Reinforcement learning and bandits for speech and language processing: Tutorial, review and outlook
Lin, B. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122254 · Cited by 28
Using ICT to Enhance Academic Learning: Pedagogy and Practice
Wang, T.-J. (2008) · Educational Research Review · doi:10.5897/err.9000402 · Cited by 34
Resource coordination in wireless sensor networks by cooperative reinforcement learning
Khan, M. I., & Rinner, B. (2012) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomw.2012.6197639 · Cited by 28
Double deep Q‐learning coordinated control of hybrid energy storage system in island micro‐grid
Yu, Y., Cai, Z., & Liu, Y. (2020) · International Journal of Energy Research · doi:10.1002/er.6029 · Cited by 28
“It is based on penalties or rewards for a series of actions taken on environmental dynamics to drive the learning process, 19,20 which is increasingly being used in the optimal control of micro-grid.”
BackgroundInterpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents
Patel, S., Wani, S., Jain, U., Schwing, A. G., Lazebnik, S., Savva, M., & Chang, A. X. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01565 · Cited by 41
“Our work is related to cooperation and coordination between multiple agents [14, 24, 27, 31, 41, 44, 45, 47, 51, 54, 55, 67].”
BackgroundToward an Automated Learning Control Architecture for Cyber-Physical Manufacturing Systems
Kovalenko, I., Moyne, J. R., Bi, M., Balta, E. C., Ma, W., Qamsane, Y., Zhu, X., Mao, Z. M., Tilbury, D. M., & Barton, K. L. (2022) · IEEE Access · doi:10.1109/access.2022.3165551 · Cited by 33
“For the learning capability in multi-agent systems, [68] and [69] mentioned explorative knowledge augmentation on a conceptual level.”
BackgroundStigmergy based behavioural coordination for satellite clusters
Tripp, H., & Palmer, P. L. (2009) · Acta Astronautica · doi:10.1016/j.actaastro.2009.09.017 · Cited by 28
“This is significant as much of the theoretical work on multi-agent coordination does not consider more than a few agents [41].”
BackgroundPolicy Distillation and Value Matching in Multiagent Reinforcement Learning
Wadhwania, S., Kim, D.-K., Omidshafiei, S., & How, J. P. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967849 · Cited by 43
“Even without specialized action spaces, homogeneous agents can learn specialized behaviours based on initial conditions or relative formations [12], meaning they can be used to solve sufficiently complex MARL problems.”
BackgroundScalable multiagent learning through indirect encoding of policy geometry
D’Ambrosio, D. B., & Stanley, K. O. (2013) · Evolutionary Intelligence · doi:10.1007/s12065-012-0086-3 · Cited by 28
“While traditional learning techniques offer potential solutions to multiagent problems [67, 97, 121], such approaches do not exploit fundamental regularities that govern the distribution of policies on a team, or the fact that such policies tend to overlap partially and can thus benefit from a…”
BackgroundMethodInfluentialWelikala, S., & Cassandras, C. G. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3034869 · Cited by 26
“Cooperative multi-agent system optimization arises in coverage control [1], formation control [2], monitoring [3], flocking [4], resource allocation [5], [6], learning [7], [8], consensus [9], [10], smart grid [11], [12], [13], transporta-”
BackgroundBanerjee, S., & Singh, G. K. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102230 · Cited by 27
Spatial Intention Maps for Multi-Agent Mobile Manipulation
Wu, J., Sun, X., Zeng, A., Song, S., Rusinkiewicz, S. M., & Funkhouser, T. A. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561359 · Cited by 39
“The same continuum of communication has been studied for multi-agent learning [14], [39], [40].”
BackgroundMulti-Layer Computation Offloading in Distributed Heterogeneous Mobile Edge Computing Networks
Wang, P., Di, B., Song, L., & Jennings, N. R. (2022) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2022.3161955 · Cited by 31
Multi-agent air combat with two-stage graph-attention communication
Sun, Z., Wu, H., Shi, Y., Yu, X., Gao, Y., Pei, W., Yang, Z. C., Piao, H., & Hou, Y. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08784-7 · Cited by 32
Shaping fitness functions for coevolving cooperative multiagent systems
Colby, M. K., & Tumer, K. (2012) · Adaptive Agents and Multi-Agents Systems · doi:10.5555/2343576.2343637 · Cited by 27
Organizing adaptation using agents in serious games
Westra, J. (2011) · Utrecht University Repository (Utrecht University) · Cited by 27
Vidhate, D. A., & Kulkarni, P. A. (2016) · International Conference on Automatic Control and Dynamic Optimization Techniques · doi:10.1109/icacdot.2016.7877588 · Cited by 26
Evolutionary Dynamics of Regret Minimization
Klos, T., van Ahee, G. J., & Tuyls, K. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15883-4_6 · Cited by 26
“Multi-agent systems (MAS) are a proven solution method for contemporary technological challenges of a distributed nature, such as e.g. load balancing and routing in networks [13,14].”
BackgroundMethodShahid, A., Aslam, S., Kim, H. S., & Lee, K. (2014) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.2800 · Cited by 26
“Although the independent learning still converges to optimal strategies as presented in [25], it takes a longer time to converge as compared with collaborative learning.”
BackgroundSearch modes for the cooperative multi-agent system solving the vehicle routing problem
Barbucha, D. (2012) · Neurocomputing · doi:10.1016/j.neucom.2011.07.032 · Cited by 26
Active Visual Planning for Mobile Robot Teams Using Hierarchical POMDPs
Zhang, S., Sridharan, M., & Washington, C. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2013.2252252 · Cited by 27
“Many algorithms have been developed for multirobot and multiagent collaboration [22], [23].”
BackgroundTeaching and leading an ad hoc teammate: Collaboration without pre-coordination
Stone, P., Kaminka, G. A., Kraus, S., Rosenschein, J. S., & Agmon, N. (2013) · Artificial Intelligence · doi:10.1016/j.artint.2013.07.003 · Cited by 38
“There are many other approaches for cooperative multiagent learning (see surveys at [61, 62, 63]).”
BackgroundCoordinated behavior of cooperative agents using deep reinforcement learning
Diallo, E. A. O., Sugiyama, A., & Sugawara, T. (2019) · Neurocomputing · doi:10.1016/j.neucom.2018.08.094 · Cited by 27
Decentralized learning for self-adaptive QoS-aware service assembly
D’Angelo, M., Caporuscio, M., Grassi, V., & Mirandola, R. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.02.027 · Cited by 26
“On the other side, concurrent learning uses multiple concurrent learning processes (e.g., one per agent) to reduce the joint space problem by projecting it into N separate subproblems [41].”
BackgroundMulti-agent Reinforcement Learning for Intrusion Detection.
Servin, A., & Kudenko⋆, D. (2007) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 26
A Cluster-Based Vehicular Cloud Architecture with Learning-Based Resource Management
Arkian, H. R., Atani, R. E., & Pourkhalili, A. (2014) · IEEE International Conference on Cloud Computing Technology and Science · doi:10.1109/cloudcom.2014.157 · Cited by 25
A survey on agents applications in healthcare: Opportunities, challenges and trends
Sulis, E., Mariani, S., & Montagna, S. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107525 · Cited by 30
“…approaches under the deep learning paradigm, the agent concept expanded to include entities capable of learning how to act in a given environment, especially through techniques belonging to or stemming from the research area of reinforcement learning and multi-agent reinforcement learning [5, 6].”
Multiagent Reinforcement Social Learning toward Coordination in Cooperative Multiagent Systems
Hao, J., Leung, H.-F., & Ming, Z. (2014) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/2644819 · Cited by 25
“One central and widely studied class of problem is how to coordinate within cooperative MASs in which the agents share common interests [Panait and Luke 2005; Matignon et al. 2012].”
BackgroundInfluentialVidhate, D. A., & Kulkarni, P. A. (2012) · International Conference on Advances in Mobile Network, Communication and Its Applications (MNCApps) · doi:10.1109/mncapps.2012.19 · Cited by 26
“Cooperation in Learning (CL) can be realized in a multi agent system, if agents are capable of learning from both their own experiments & other agents' knowledge[4].”
BackgroundCloud-based centralized/decentralized multi-agent optimization with communication delays
Hale, M., Nedić, A., & Egerstedt, M. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402311 · Cited by 25
Moarref, S., & Kress‐Gazit, H. (2019) · Autonomous Robots · doi:10.1007/s10514-019-09861-4 · Cited by 28
A Multitier Reinforcement Learning Model for a Cooperative Multiagent System
Shi, H., Zhai, L., Wu, H., Hwang, M., Hwang, K., & Hsu, H.-P. (2020) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.2970487 · Cited by 24
“For example, in cooperation conveying [22], the wrong coordination between agents will make goods drop and the agents cannot move.”
BackgroundKo, B., Ryu, S., Park, B., & Son, S. H. (2020) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2019.0709 · Cited by 28
Towards Reinforcement Learning-based Aggregate Computing
Aguzzi, G., Casadei, R., & Viroli, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-08143-9_5 · Cited by 26
“swarm robotics [37]) is to add another constraint, namely the agents’ homogeneous and cooperative behaviour [33].”
BackgroundLearning from experts in cognitive radio networks: The docitive paradigm
Galindo‐Serrano, A., Giupponi, L., Blasco, P., & Döhler, M. (2010) · International Conference on Cognitive Radio Oriented Wireless Networks (CROWNCOM) · doi:10.4108/icst.crowncom2010.9173 · Cited by 24
“Gains are expected due to a high correlation in the environments of adjacent expert and newcomer nodes.”
BackgroundThe dynamics of reinforcement social learning in cooperative multiagent systems
Hao, J., & Leung, H.-F. (2013) · Cited by 24
Target shape design optimization by evolving B-splines with cooperative coevolution
Yang, Z., Sendhoff, B., Tang, K., & Yao, X. (2016) · Applied Soft Computing · doi:10.1016/j.asoc.2016.07.027 · Cited by 24
Optimizing time warp simulation with reinforcement learning techniques
Wang, J., & Tropper, C. (2007) · Winter Simulation Conference · doi:10.1109/wsc.2007.4419650 · Cited by 24
“Obviously, the multi-agent setting is much more complex than that of the single-agent, because each agent s learning process is affected by other agents, and usually some sort of coordination among the agents is required for the learning to be effective(Panait and Luke 2005).”
BackgroundQ-learning based hyper-heuristic for scheduling system self-parameterization
Falcão, D., Madureira, A. M., & Pereira, I. F. (2015) · Iberian Conference on Information Systems and Technologies (CISTI) · doi:10.1109/cisti.2015.7170394 · Cited by 23
“sequences of actions on the environment [10].”
A Thorough Insight into Theoretical and Practical Developments in MultiAgent Systems
Juneja, D., Singh, A., Singh, R., & Mukherjee, S. (2017) · International Journal of Ambient Computing and Intelligence · doi:10.4018/ijaci.2017010102 · Cited by 23
“Simply speaking, a software agent is a software component capable of carrying out rational and self-directed actions in a typical multi-agent system (Panait & Luke, 2005; Hoek, Wiebe 23 International Journal of Ambient Computing and Intelligence Volume 8 • Issue 1 • January-March 2017 24 &…”
MethodResilient Multi-Agent Reinforcement Learning with Adversarial Value Decomposition
Phan, T., Belzner, L., Gabor, T., Sedlmeier, A., Ritz, F., & Linnhoff–Popien, C. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17348 · Cited by 39
“MARL is a long-standing AI research area with various approaches (Tan 1993; Panait and Luke 2005; Foerster et al. 2018; Son et al. 2019).”
BackgroundHeuristics for determining a patrol path of an unmanned combat vehicle
Park, C., Kim, Y., & Jeong, B. (2012) · Computers & Industrial Engineering · doi:10.1016/j.cie.2012.02.007 · Cited by 25
Matignon, L., Laurent, G. J., Fort-Piat, N. L., & Chapuis, Y. A. (2010) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-010-9396-9 · Cited by 25
“The proposed control architecture is based on the game theory perspective, where a team of agents are cooperating to solve a joint task [24,7].”
Self-Organizing mm Wave Networks: A Power Allocation Scheme Based on Machine Learning
Amiri, R., & Mehrpouyan, H. (2018) · Global Symposium on Millimeter-Waves · doi:10.1109/gsmm.2018.8439323 · Cited by 25
“Independent learning has shown good performance in many applications [10].”
BackgroundA Mean Field Game Approach to Swarming Robots Control
Liu, Z., Wu, B., & Lin, H. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8431807 · Cited by 43
“Generally, these bottom-up approaches, including evolutionary robotics [11] and reinforcement learning [12], cannot guarantee to achieve the desired global behavior.”
BackgroundParallel Transfer Learning in Multi-Agent Systems: What, when and how to transfer?
Taylor, A., Dusparić, I., Guériau, M., & Clarke, S. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851784 · Cited by 23
“b) Co-operative Predator-Prey Pursuit: A team of preda tors must catch prey [12], [13].”
BackgroundMohammadisarab, A., Nouruzi, A., Khalili, A., Mokari, N., Arand, B. A., & Jorswieck, E. A. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3376335 · Cited by 32
“Instead of updating online, all trajectories are saved in replay buffer D in order to learn with the minibatch updating [62].”
Heterogeneous team deep q-learning in low-dimensional multi-agent environments
Kurek, M., & Jaśkowski, W. (2016) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2016.7860413 · Cited by 21
“In the final experiment, we ask the question whether it pays off to learn a separate policy for each agent, which is often called heterogeneous team learning [19].”
BackgroundNitsche, B., Brands, J., Treiblmaier, H., & Gebhardt, J. (2023) · Supply Chain Management An International Journal · doi:10.1108/scm-07-2022-0282 · Cited by 30
Collet, J., Morford, J., Lewin, P. J., Bonnet‐Lebrun, A., Sasaki, T., & Biro, D. (2023) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2022.0060 · Cited by 30
“Panait L, Luke S. 2005 Cooperative multi-agent learning: the state of the art.”
BackgroundInfluentialA Multi-State Q-Learning Approach for the Dynamic Load Balancing of Time Warp
Meraji, S., Zhang, W., & Tropper, C. (2010) · ACM/IEEE/SCS Workshop on Principles of Advanced and Distributed Simulation (PADS) · doi:10.1109/pads.2010.5471661 · Cited by 22
Paquet, E. (2006) · Cited by 22
Coevolutionary bid-based genetic programming for problem decomposition in classification
Lichodzijewski, P., & Heywood, M. I. (2008) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-008-9067-9 · Cited by 22
“Multi-agent models of problem solving also provide a natural metaphor for problem decomposition [35].”
BackgroundSelf-Organizing Neural Architectures and Cooperative Learning in a Multiagent Environment
Xiao, D., & Tan, A. (2007) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2007.907040 · Cited by 22
Savino, S. D., Minella, T., Nagy, Z., & Capozzoli, A. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.125993 · Cited by 26
“This facilitates more effective coordination of agents’ actions [15].”
Mozafari, M., Shiri, M. E., & Hamid Beigy, A. (2015) · Journal of Computational Science · doi:10.1016/j.jocs.2015.08.002 · Cited by 21
“Cooperative learning techniques [26] are a class of techniques that are designed to address coopera40”
BackgroundA Mutual Influence Detection Algorithm for Systems with Local Performance Measurement
Rudolph, S., Tomforde, S., Sick, B., & Hähner, J. (2015) · IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) · doi:10.1109/saso.2015.23 · Cited by 20
Acan, A., & Lotfi, N. (2016) · Artificial Intelligence Review · doi:10.1007/s10462-016-9493-7 · Cited by 22
“A full list properties associated with intelligent agents can be found in Panait and Luke (2005).”
BackgroundChumkamon, S., Hayashi, E., & Koike, M. (2016) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2016.09.004 · Cited by 21
Compiler Test-Program Generation via Memoized Configuration Search
Chen, J., Suo, C., Jiang, J., Chen, P., & Li, X. (2023) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse48619.2023.00172 · Cited by 32
“Besides, as presented by the existing work [37], multi-agent RL outperforms single-agent RL especially when the state-action space of single-agent RL is large (like our scenario), as the large state-action space can cause both ANN and CNN hard-to-converge, leading to inaccurate prediction.”
BackgroundOrganisational adaptation of multi-agent systems in a peer-to-peer scenario
Jordi Campos, A., Esteva, M., López-Sánchez, M., Morales, J., & Salamó, M. (2010) · Computing · doi:10.1007/s00607-010-0141-9 · Cited by 26
“In fact, the cooperative MAS learning taxonomy in [38] highlights the complexity of such a task since agent interactions may bring unexpected joint behaviour—i.”
BackgroundTask partitioning in a robot swarm: a study on the effect of communication
Pini, G., Gagliolo, M., Brutschy, A., Dorigo, M., & Birattari, M. (2013) · Swarm Intelligence · doi:10.1007/s11721-013-0078-7 · Cited by 22
“Only limited work in multi-agent learning deals with some form of social learning (see Panait and Luke 2005, for a review).”
BackgroundCollaborative signal and information processing in wireless sensor networks: A review
Bal, M., Shen, W., & Ghenniwa, H. H. (2009) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2009.5346152 · Cited by 21
“The batteries of each sensor node in the field might be very difficult to replace.”
Dynamic Team Heterogeneity in Cooperative Coevolutionary Algorithms
Gomes, J., Mariano, P., & Christensen, A. L. (2017) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2017.2779840 · Cited by 20
“to design multiagent control, heterogeneity complicates the learning process [1], [3], as the size of the search space becomes proportional to the number of different agents.”
BackgroundMethodInfluentialA multiagent framework for learning dynamic traffic management strategies
Chung, J. J., Rebhuhn, C., Yates, C., Hollinger, G. A., & Tumer, K. (2018) · Autonomous Robots · doi:10.1007/s10514-018-9800-z · Cited by 22
Adaptable mobile cloud computing environment with code transfer based on machine learning
Nawrocki, P., Śnieżyński, B., & Slojewski, H. (2019) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2019.05.001 · Cited by 23
Social Internet of Energy—A New Paradigm for Demand Side Management
Caballero, V., Vernet, D., & Zaballos, A. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2932508 · Cited by 25
“References [47]–[49] support the idea that a mid-large-scale SG is likely to be managed in a cooperatively and more autonomously manner with multiple agents involved.”
BackgroundDrone mapping through multi-agent reinforcement learning
Zanol, R., Chiariotti, F., & Zanella, A. (2019) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc.2019.8885873 · Cited by 25
“In general, there are several ways to approach multi-agent RL [17]: one extreme is a fully centralized controller dictating the actions of all agents with a full picture of the overall state of the system, which avoids the coordination problem but significantly increases the complexity of the problem and the communica…”
Self-Organizing Cognitive Agents and Reinforcement Learning in Multi-Agent Environment
Tan, A., & Xiao, D. (2006) · IEEE/WIC/ACM International Conference on Intelligent Agent Technology · doi:10.1109/iat.2005.125 · Cited by 23
“The minefield pursuit task is more challenging than a typical predator and prey task [10] as each predator needs to avoid stepping into mines while pursuing the target.”
BackgroundThe Self-Adaptive Context Learning Pattern: Overview and Proposal
Boes, J., Nigon, J., Verstaevel, N., Gleizes, M.-P., & Migeon, F. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25591-0_7 · Cited by 20
Multiagent Systems in Construction: A Ten-Year Review
Liang, X., Shen, Q., & Bu, S. (2016) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000574 · Cited by 25
Distributed optimization in multi-agent robotics for industry 4.0 warehouses
Kattepur, A., Rath, H. K., Simha, A., & Mukherjee, A. (2018) · ACM Symposium on Applied Computing · doi:10.1145/3167132.3167221 · Cited by 21
“Co-ordinating such devices in a decentralized setting is an active area of research [14].”
BackgroundReputation Based Trust In Human-Agent Teamwork Without Explicit Coordination
Hafızoğlu, F. M., & Sen, S. (2018) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3284432.3284454 · Cited by 21
“This “moving target” learning problem is well-recognized in the multi-agent learning literature [28].”
BackgroundZhou, H., Lan, T., & Aggarwal, V. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3293193 · Cited by 38
“Even though multi-agent cooperative problems could be solved by single-agent algorithms, joint state, and action space imply limited scalability [29], [41].”
BackgroundA Real-Time Computational Learning Model for Sequential Decision-Making Problems Under Uncertainty
Malikopoulos, A. A., Papalambros, P. Y., & Assanis, D. N. (2009) · Journal of Dynamic Systems Measurement and Control · doi:10.1115/1.3117200 · Cited by 24
A Cooperative Multiagent Based Spectrum Sharing
Mir, U., Merghem, L., & Gaïti, D. (2010) · International Conference on Internet and Web Applications and Services · doi:10.1109/aict.2010.31 · Cited by 20
Incorporating Bayesian learning in agent-based simulation of stakeholders’ negotiation
Pooyandeh, M., & Marceau, D. J. (2014) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2014.07.003 · Cited by 24
Jiang, G., Hu, B., & Wang, Y. (2010) · SIMULATION · doi:10.1177/0037549710385745 · Cited by 25
“D(30-60) D(20-70) D(10-80) Task Nums (25) C ap ab ili ty in cr ea se V1 V2 V3 Avg”
Masoumzadeh, S. S., & Hlavacs, H. (2015) · IEEE Symposium on Network Cloud Computing and Applications (NCCA) · doi:10.1109/ncca.2015.17 · Cited by 20
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.