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 601–700 of 1,000
Selfish optimization and collective learning in populations
McAvoy, A., Mori, Y., & Plotkin, J. B. (2022) · Physica D Nonlinear Phenomena · doi:10.1016/j.physd.2022.133426 · Cited by 7
“In contrast, the goal of multiagent reinforcement learning is to optimize an agent’s success or fitness in the presence of other agents, who themselves might be carrying out a similar kind of optimization [7, 8].”
BackgroundLearning Cooperative Neural Modules for Stylized Image Captioning
Wu, X., Zhao, W., & Luo, J. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01636-2 · Cited by 9
“In this case, it is difficult for the sentence-level reward to distinguish the contribution of each word, referred to as credit assignment problem (Panait and Luke, 2005).”
BackgroundAdaptive Cyber Defense Technique Based on Multiagent Reinforcement Learning Strategies
Alshamrani, A., & Alshahrani, A. (2023) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.032835 · Cited by 7
Collective point-to-point iterative learning control of multi-agent system with switched reference
Zhao, X., Tuo, J., & Wang, Y. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.07.033 · Cited by 6
Real-Time Training of Team Soccer Behaviors
Sullivan, K. M., & Luke, S. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39250-4_32 · Cited by 6
“) rather than supervised learning [23].”
MethodSelf-citationSon, J.-H., & Ahn, H. (2008) · IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications · doi:10.1109/mesa.2008.4735723 · Cited by 6
Self-optimizing through CBR learning
Pereira, I. F., & Madureira, A. M. (2010) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2010.5586081 · Cited by 6
“Case-based Reasoning (CBR) revealed to be an appropriate approach for scheduling systems and is a good learning technique to apply a Team Learning approach [ 21 ] in a Scheduling MAS.”
BackgroundMethodA comparison of a communication strategies in cooperative learning
Solomon, M., Soule, T., & Heckendorn, R. B. (2012) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2330163.2330185 · Cited by 6
Graña, M., Fernandez‐Gauna, B., & López-Guede, J. M. (2011) · Paladyn Journal of Behavioral Robotics · doi:10.2478/s13230-011-0017-5 · Cited by 6
Evolving a multiagent coordination strategy using Genetic Network Programming for pursuit domain
Naeini, A. T., & Palhang, M. (2008) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2008.4631217 · Cited by 6
“The field of cooperative multiagent learning promises solutions to these issues by employing automatic search methods to discover agent behaviors, and as such it has been the focus of numerous studies in recent years [3].”
BackgroundObject-Oriented Reinforcement Learning in Cooperative Multiagent Domains
da Silva, F. L., Glatt, R., & Costa, A. H. R. (2016) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2016.015 · Cited by 6
Grounded Semantic Networks for Learning Shared Communication Protocols
Stone, M. H. A. P. (2016) · Cited by 6
Adaptive mobile behavior change intervention using reinforcement learning
Cai, L., Wu, C., Meimandi, K. J., & Gerber, M. S. (2017) · doi:10.1109/companion.2017.8287078 · Cited by 6
“Rather than positing a single, monolithic RL agent capable of interacting with all agents in this heterogeneous environment, we propose the use of multiple cooperative RL agents [8] that interact with the various parties (e.”
BackgroundPerformance of a multi-agent system over a multi-core cluster managed by Terracotta
Cicirelli, F., Furfaro, A., Giordano, A., & Nigro, L. (2011) · doi:10.5555/2048476.2048492 · Cited by 6
MULTI-AGENT BASED INFORMATION SYSTEMS FOR PATIENT COORDINATION IN HOSPITALS
Paulussen, T. O., Heinzl, A., & Becker, C. (2013) · Journal of the Association for Information Systems · Cited by 6
Distributed Problem Solving using Evolutionary Learning in Multi-Agent Systems
Srinivasan, D., & Choy, M. C. (2007) · Studies in computational intelligence · doi:10.1007/978-3-540-72377-6_9 · Cited by 6
“The hybrid multi-agent approach has been applied in a wide spectrum of application domains concerning commerce, manufacturing, defense, etc. by many researchers in recent years [ 5 ].”
BackgroundA Reinforcement Learning Approach for Interdomain Routing with Link Prices
Vrancx, P., Gurzì, P., Rodríguez, A., Steenhaut, K., & Nowé, A. (2015) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/2719648 · Cited by 6
CLEAN Rewards to Improve Coordination by Removing Exploratory Action Noise
HolmesParker, C., Taylor, M. E., Agogino, A., & Tumer, K. (2014) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2014.159 · Cited by 6
Scaling multi-agent learning in complex environments
Lesser, V., & Zhang, C. (2011) · Cited by 7
Learning Chasing Behaviours of Non-Player Characters in Games Using SARSA
Phon-Amnuaisuk, S. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20525-5_14 · Cited by 6
“We could require for the NPCs to cooperate in order to complete a given task [ 7 ], [9].”
MethodIntegrated the Intelligent Agent Behavior Model and Billing Service into Communication System
Lo, S. K. C., Keh, H., Lin, Y.-H., & Jo-Chi, W. (2009) · Information Technology Journal · doi:10.3923/itj.2009.668.677 · Cited by 6
Evolutionary stability affected by energy flow in the bio-network architecture
Sun, H., Ren, L., & Ding, Y. (2008) · Neurocomputing · doi:10.1016/j.neucom.2008.05.015 · Cited by 6
Agentification of Individuals: A Multi-Agent Approach to Metaheuristics
Aydın, M. E. (2013) · Journal of Computer Science & Systems Biology · doi:10.4172/jcsb.1000e105 · Cited by 6
Social Learning and Adoption of New Behavior in a Virtual Agent Society
Nye, B. D., & Silverman, B. G. (2013) · PRESENCE Virtual and Augmented Reality · doi:10.1162/pres_a_00144 · Cited by 6
“However, from a literature standpoint, CAS simulations that include social learning typically use lightweight agents and depend on one or two simple mechanisms that implement normative theories, such as game-theoretic agents (Panait & Luke, 2005).”
BackgroundA robust crew pairing based on Multi-agent Markov Decision Processes
Aoun, O., & Afia, A. E. (2014) · World Conference on Complex Systems · doi:10.1109/icocs.2014.7060940 · Cited by 6
“The reward function is defined widely to all Agents, while stochastic games (Liviu Panait et al.[24]) define a function for each agent reward.”
BackgroundDimensions of Cooperative Control
Shamma, J. S., & Arslan, G. (2007) · doi:10.1002/9780470724200.ch1 · Cited by 6
“Other reviews of cooperative control and related research may be found in Murray (2006) and Panai and Luke (2005) .”
BackgroundDecentralized Coordinated Optimal Ramp Metering using Multi-agent Reinforcement Learning
Rezaee, K. (2014) · TSpace (University of Toronto) · Cited by 6
Accelerating Training in Pommerman with Imitation and Reinforcement LearningPreprint
Meisheri, H., Shelke, O., Verma, R., & Khadilkar, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.04947 · Cited by 10
Li, Y., Wang, L., Yang, J., Wang, E. B., Wang, Z., Zhao, T., & Zha, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08268 · Cited by 27
“To tackle this challenge, we focus on cooperative MARL , where agents work together to maximize their team reward (Panait and Luke, 2005).”
BackgroundVaillant, Y., Lafuente, E., & Vendrell-Herrero, F. (2026) · International Journal of Production Economics · doi:10.1016/j.ijpe.2026.109931 · Cited by 8
Ray, D. N., Mandal, A. K., Majumder, S., & Mukhopadhyay, S. (2011) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2011.6181717 · Cited by 5
Information Sharing for Cooperative Robots via Multi-Agent Reinforcement Learning
Siddiqua, A., Liu, S., Iqbal, R., Ross, L., Zweerink, B., & Eskridge, R. (2024) · IEEE International Symposium on Robotic and Sensors Environments · doi:10.1109/rose62198.2024.10590879 · Cited by 5
“They discussed the challenges of tackling joint team tasks, highlighting the significance of team learning and effective communication among learning agents [2].”
BackgroundZhuang, H., Wu, S., Razoumny, V. Y., & Razoumny, Y. N. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130576 · Cited by 5
Critic learning in multi agent credit assignment problem
Rahaie, Z., & Hamid Beigy, A. (2016) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/ifs-162093 · Cited by 5
Quantifying the impact of communication on performance in multi-agent teams
Zuparic, M. L., Jauregui, V., Prokopenko, M., & Yue, Y. (2017) · Artificial Life and Robotics · doi:10.1007/s10015-017-0367-0 · Cited by 5
“Panait and Luke [50], in their survey of the space of multi-agent learning, explore scenarios in which agents benefit by communicating to solve a collective problem, viz., cooperative multi-agent learning.”
BackgroundOnline Multi-Objective Model-Independent Adaptive Tracking Mechanism for Dynamical Systems
Abouheaf, M., Gueaieb, W., & Spinello, D. (2019) · Robotics · doi:10.3390/robotics8040082 · Cited by 5
“The cooperative multi-agent learning systems use the interactions among the agents to accomplish joint tasks in [52].”
BackgroundFacchini, S. D. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/828 · Cited by 5
Attention-Cooperated Reinforcement Learning for Multi-agent Path Planning
Ma, J., & Lian, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-11217-1_20 · Cited by 6
Oliva, G., Rikos, A. I., Gasparri, A., & Hadjicostis, C. N. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3161612 · Cited by 5
“Cooperativemultiagentsystemsinvolveanumberofentitiesworking together to collectively solve a problem or maximize utility [1].”
BackgroundDistributed Formation Control for a Class of Human-in-the-Loop Multiagent Systems
Zhang, X.-X., Wu, H., & Wang, J.-L. (2024) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2024.3398631 · Cited by 5
“D ISTRIBUTED cooperative control of multiagent systems (MASs) has gained much attention owing to the wide range of applications [1], [2], [3], [4], [5].”
BackgroundCollaborative multi-agent reinforcement learning based on experience propagation
Fang, M., & Groen, F. C. A. (2013) · Journal of Systems Engineering and Electronics · doi:10.1109/jsee.2013.00079 · Cited by 5
Vinagre, G., Valério, D., Beirão, P. J. B. F. N., & da Costa, J. S. (2012) · Procedia - Social and Behavioral Sciences · doi:10.1016/j.sbspro.2012.05.403 · Cited by 5
Fang, M., Groen, F. C. A., Li, H., & Zhang, J.-J. (2013) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2013.09.001 · Cited by 5
Neuroevolution of Controllers for Self-Organizing Mobile Ad Hoc Networks
Knoester, D. B., & McKinley, P. K. (2011) · IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) · doi:10.1109/saso.2011.30 · Cited by 5
“///SSSAAASSSOOO...222000111111...333000 111888888”
A novel approach to spectrum management in cognitive radio networks using agent coalition formation
Benidris, F. Z., Benmammar, B., & Krief, F. (2015) · International Journal of Wireless and Mobile Computing · doi:10.1504/ijwmc.2015.071666 · Cited by 5
“We start here by defining an agent as a dynamic and loosely coupled unit, having the capabilities of performing a task autonomously, based on the knowledge received from its environment and/or through other agents’ interactions (Panait and Luke, 2005).”
BackgroundA Mutual Influence-based Learning Algorithm
Rudolph, S., Tomforde, S., & Hähner, J. (2016) · International Conference on Agents and Artificial Intelligence (ICAART) · doi:10.5220/0005697001810189 · Cited by 5
“These works all belong to one of two categories: (i) team learning where a single learner is used for all the agents or (ii) concurrent learner where each agent has an own learner (Panait and Luke, 2005).”
InfluentialCooperative multi-agent reinforcement learning in a large stationary environment
Zemzem, W., & Tagina, M. (2017) · IEEE/ACIS International Conference on Computer and Information Science (ICIS) · doi:10.1109/icis.2017.7960020 · Cited by 5
“This class of approaches studies the problem of an agent that learns based on both reward and punishment received from the environment and it has been widely studied [2] [3] [4].”
Distributed Optimization Framework for Industry 4.0 Automated Warehouses
Kattepur, A., Rath, H. K., Mukherjee, A., & Simha, A. (2018) · EAI Endorsed Transactions on Industrial Networks and Intelligent Systems · doi:10.4108/eai.27-6-2018.155237 · Cited by 5
A Decentralized Mobile Computing Network for Multi-Robot Systems Operations
Kit, J. L., Mateo, D., & Bouffanais, R. (2018) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon.2018.8796753 · Cited by 5
“using collective reinforcement learning [15].”
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory
Leonardos, S., & Piliouras, G. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17343 · Cited by 10
Collet, J., Sasaki, T., & Biro, D. (2021) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2021.2110 · Cited by 7
“In particular, within a group acting collectively, individual members may each experience a weaker association between their own contribution and the resulting costs or benefits, compared to individual learners [33,34], and it is known that weaker associations between cues and rewards can affect long-term storage and/…”
BackgroundPreference communication in multi-objective normal-form games
Röpke, W., Roijers, D. M., Nowé, A., & Rădulescu, R. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07533-6 · Cited by 9
“Lastly, communication has been explored in cooperative MARL settings, showing its applicability and benefits [7, 18].”
Investigating vesicular selection
Lee, Y.-G., McKay, B., Kim, K.-I., Kim, D., & Hoài, N. X. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2011.05.006 · Cited by 6
Non-reciprocating Sharing Methods in Cooperative Q-Learning Environments
Cunningham, B. W., & Cao, Y. (2012) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2012.28 · Cited by 7
“a computational mechanism that exhibits a high degree of autonomy, performing actions in its environment based on information (sensors, feedback) received from the environment” [38].”
BackgroundMethodInfluentialA hybrid genetic programming decision making system for RoboCup soccer simulation
Tavafi, A., & Banzhaf, W. (2017) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3071178.3071194 · Cited by 5
“…different method than Luke’s team for evolving their players and they employed an optional coach agent - who receives noiseless data from the server but has very limited communication with agents-for storing data and coordinating the decision for rewarding players after each command execution [17].”
MethodEvolved communication strategies and emergent behaviour of multi-agents in pursuit domains
Grossi, G., & Ross, B. J. (2017) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2017.8080423 · Cited by 5
“Communication strategies [1] are divided into two parts, the actual language (commands) used to communicate and the communication channel.”
BackgroundInfluentialEffect of Multiple-Agent Deployment in MANET
Mahapatra, B., Patnaik, S., & Nayyar, A. (2018) · Recent Advances in Computer Science and Communications · doi:10.2174/2213275911666180829104117 · Cited by 5
A Framework For Autonomous Heterogeneous Robot Teams
Roos, T., & Emami, M. R. (2018) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2018.8581303 · Cited by 5
“Techniques such as reinforcement learning or evolutionary algorithms would enable each robot to develop a policy to map its states to appropriate actions [5].”
BackgroundOnline Learning and Teaching of Emergent Behaviors in Multi-Robot Teams
Costa, L. F. S., Nascimento, T., & Gonçalves, L. M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2951013 · Cited by 5
Mirzaei, F., Pouyan, A. A., & Biglari, M. (2020) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-020-01201-4 · Cited by 5
Inference-Based Deterministic Messaging For Multi-Agent Communication
Bhatt, V., & Buro, M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17339 · Cited by 5
Agent Based Onboard Firefighting System
Sumić, D., Maleš, L., & Rosić, M. (2021) · Transactions on Maritime Science · doi:10.7225/toms.v10.n01.007 · Cited by 5
“Most real-world problems require or involve multiple agents to account for the decentralized nature of the problem, provide multiple perspectives, or present competing interests (Panait & Luke, 2005).”
BackgroundMarie, F., & Haddour, N. (2009) · InTech eBooks · doi:10.5772/7876 · Cited by 5
Learning Cooperative Behaviours in Multiagent Reinforcement Learning
Phon-Amnuaisuk, S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10677-4_65 · Cited by 5
“There are good surveys from [14], [18], [ 12 ] and recently by [3] which we would not want to repeat here, though we would touch on some closely related works again for background information.”
BackgroundNorm Emergence with Biased Agents
Mukherjee, P., Sen, S., & Airiau, S. (2009) · International Journal of Agent Technologies and Systems · doi:10.4018/jats.2009040105 · Cited by 5
Towards a deeper understanding of cooperative equilibrium: characterization and complexity
Rong, N., & Halpern, J. Y. (2013) · doi:10.5555/2484920.2484973 · Cited by 5
Improving learning in robot teams through personality assignment
Recchia, T., Chung, J. H., & POCHIRAJU, K. V. (2012) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2012.09.003 · Cited by 5
A developmental approach to evolving scalable hierarchies for multi-agent swarms
Soule, T., & Heckendorn, R. B. (2010) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/1830761.1830802 · Cited by 5
“Although systems consisting of many agents can be reliably trained via EC to perform well, it has not been shown that the learned behaviors can be reliably translated into teams with 10× to 1000× as many agents [5, 28, 29].”
BackgroundMulti-agent PID and fractional PID control of the three-tank benchmark system
Vinagre, G., Valério, D., & da Costa, J. S. (2010) · UKACC International Conference on Control · doi:10.1049/ic.2010.0442 · Cited by 5
“Notice that this “Main” agent preserves the characteristics of a multi-agent system: all agents are autonomous (at least partially), have a local view of the system (they depend on one another for a full global view of the system, and if agent communications fail they will lack this global view), and are decentralised…”
BackgroundAdaptive Complex Systems: Digital Twins
Clark, T., & Kulkarni, V. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-818576-6.00011-3 · Cited by 7
Evolution of cooperation in artificial ants
Waibel, M. (2007) · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · doi:10.5075/epfl-thesis-3943 · Cited by 5
Evolutionary optimization of cooperative heterogeneous teams
Soule, T., & Heckendorn, R. B. (2007) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.724018 · Cited by 5
“For an overview of the field see Paniut and Luke.4 Research has shown the evolutionary techniques, including both genetic algorithms (GAs) and genetic programming (GP), are extremely effective at evolving multi-agent teams.”
BackgroundAutonomous information fusion for robust obstacle localization on a humanoid robot
Sridharan, M., & Li, X. (2009) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars.2009.5418328 · Cited by 5
“Information communicated by teammates can be merged to obtain robust estimates about areas that are hidden from the robot’s field of view, which would prove very useful in surveillance scenarios [9].”
BackgroundA Visual Communication Map for Multi-Agent Deep Reinforcement LearningPreprint
Nguyen, N. D., Nguyen, T. T., Creighton, D., & Nahavandi, S. (2020) · arXiv (Cornell University) · doi:10.13140/rg.2.2.13433.62563 · Cited by 9
“M ULTI-AGENT learning is to learn the interaction be-tween multiple distributed self-operated agents to balance a shared interest or collectively achieve a designated objective [1], [2].”
BackgroundReducing overestimation with attentional multi-agent twin delayed deep deterministic policy gradient
Cao, Y., Tian, Z., Liu, Z., Jia, N., & Liu, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110352 · Cited by 8
Yoon, J., Ahn, K., Lee, K., Park, J., & Yeo, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3548945 · Cited by 5
“As it is shown that learning the effect of joint actions is more effective than the independent learning [18], [19], [20], recent studies propose methodologies for obtaining a cooperative solution.”
Wang, X., D’Ariano, A., Su, S., Tang, T., Su, B., & Yan, M. (2025) · Computers & Industrial Engineering · doi:10.1016/j.cie.2025.111244 · Cited by 4
Duan, Y., Huang, J., Zhang, Z., & Deng, H. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3578626 · Cited by 5
“There are two main sources of this complexity: larger cluster sizes and task heterogeneity [5].”
Zhu, G., Zhang, F., Ranjan, R. K., Dustdar, S., Li, J., Wang, Y., Wang, Y., Huang, X., Chen, Y., & Wang, L. (2025) · IEEE Internet Computing · doi:10.1109/mic.2025.3566787 · Cited by 4
“The overall technical framework is shown in Figure 4, which combines multi-agent systems (MASs) 11 and LLMs within the emergency management domain.”
Introducing the Concept of Hyperactivity in Multi Agent Systems
Nagrath, V., Mériaudeau, F., Malik, A. S., & Morel, O. (2013) · International Conference on Communication Systems and Network Technologies · doi:10.1109/csnt.2013.117 · Cited by 4
“Unlike DPS which deals with the distribution of the process of problem solving, MAS highlights the behavioral and interaction related complexities [6].”
BackgroundEvolving robot swarm behaviors by minimizing surprise: results of simulations in 2-d on a Torus
Borkowski, R., & Hamann, H. (2017) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3067695.3082548 · Cited by 4
“The evolution or learning of multi-agent behaviors is known to be challenging [7].”
BackgroundImportance of prefrontal meta control in human-like reinforcement learning
Lee, J. H., Leibo, J. Z., An, S.-J., & Lee, S. W. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.1060101 · Cited by 5
“This case is important for many applications (Claus and Boutilier, 1998; Panait and Luke, 2005).”
BackgroundBretas, A. M. C., Mendes, A. S., Chalup, S. K., Jackson, M., Clement, R., & Sanhueza, C. (2023) · Expert Systems · doi:10.1111/exsy.13315 · Cited by 6
“According to Panait and Luke (2005), a MAL task arises when multiple learning agents share the same environment.”
Multi-agent learning via gradient ascent activity-based credit assignment
Sabri, O., Lehéricy, L., & Muzy, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-42448-9 · Cited by 4
The Sustainable Foraging Problem
Aishwaryaprajna, N. A., & Lewis, P. R. (2023) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C) · doi:10.1109/acsos-c58168.2023.00047 · Cited by 4
“The cooperation between the agents is often key in the context of these goal-oriented short-term tasks of efficient resource collection [3].”
BackgroundApproximate Policy Iteration for Robust Stochastic Control of Multiagent Markov Decision Processes
Huang, F., Cao, M., & Wang, L. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3510596 · Cited by 5
“…(MDPs) [7] (also referred to as team Markov games [8], [9]/Markov teams [6]) describe a fully cooperative multiagent system, in which a group of agents works together, through interactions, coordination, and information-sharing, to collectively accomplish a task or achieve a goal [7], [10].”
Ruiz, C., Bhatt, P. M., Gupta, S. K., & Huang, Q. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3532179 · Cited by 4
“For rough identification of boundary regions, the learning-agents can be trained as a team [32] with homogeneous search rules and minimal communication of the position of other learning-agents in the team.”
Cooperative induction of decision trees
Bazzan, A. L. C. (2013) · doi:10.1109/ia.2013.6595190 · Cited by 4
“Several approaches to MARL have been proposed; since a comprehensive discussion is not possible here, we refer the reader to [16].”
Evolutionary Inheritance Mechanisms for Multi-criteriaDecision Making in Multi-agent Systems
Moritz, R. L. V., & Middendorf, M. (2015) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2739480.2754773 · Cited by 4
“Also as part of multi-agent systems such evolutionary principles have been used, e.g. in [11, 12, 14, 15].”
BackgroundA recursive genetic framework for evolutionary decision-making in problems with high dynamism
Pashaei, K., Taghiyareh, F., & Badie, K. (2014) · International Journal of Systems Science · doi:10.1080/00207721.2013.879225 · Cited by 4
“The main issue with the credit assignment is the inability to divide the reward obtained at team levels among individual agents (Panait & Luke, 2005).”
BackgroundInfluentialApplying Reinforcement Learning in Formation Control of Agents
Derhami, V., & Momeni, Y. (2015) · Studies in computational intelligence · doi:10.1007/978-3-319-25017-5_28 · Cited by 4
“If all agents receive the same reward, this approach is called global reward, but in local reward method every agent receives its reward based solely on its individual behavior [11].”
BackgroundMulti‐level decision making in hierarchical multi‐agent robotic search teams
Nasir, A., Salam, Y., & Saleem, Y. (2016) · The Journal of Engineering · doi:10.1049/joe.2016.0076 · Cited by 4
Vidhate, D. A., & Kulkarni, P. A. (2017) · Smart innovation, systems and technologies · doi:10.1007/978-3-319-63645-0_39 · Cited by 4
Multi-agent Cooperation Models by Reinforcement Learning (MCMRL)
Deepak, A., & Kulkarni, P. A. (2017) · International Journal of Computer Applications · doi:10.5120/ijca2017915511 · Cited by 4
GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS
Kabysh, A., & Golovko, V. A. (2014) · International Journal of Computing · doi:10.47839/ijc.11.3.566 · Cited by 4
“Типовые задачи, решаемые в теории многоагентных, систем включают в себя [1] автоматизированный трейдинг, ведение переговоров, управление нагрузкой сети, организация коллектива роботов-футболистов, распределенная оптимизация, распределенное планирование задач [2] и другие.”
Al-Hussaini, S., Gregory, J. M., & Gupta, S. K. (2018) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2018.8468614 · Cited by 5
“suited for the domain of reinforcement learning (RL), for which there are many existing approaches [5], including applications in robotics [6] and multi-agent systems [7], [8].”
BackgroundA Top-Down Approach to Attain Decentralized Multi-agents
Lin, A. T., Montúfar, G., & Osher, S. (2021) · Studies in systems, decision and control · doi:10.1007/978-3-030-60990-0_14 · Cited by 3
Reinforcement Learning Based Hierarchical Multi-Agent Robotic Search Team in Uncertain Environment
Hamid, S., Nasir, A., & Saleem, Y. (2021) · Mehran University Research Journal of Engineering and Technology · doi:10.22581/muet1982.2103.17 · Cited by 6
“Both of these approaches are a part of distributed artificial intelligence [25].”
BackgroundMean Field Equilibrium in Multi-Armed Bandit Game with Continuous Reward
Wang, X., & Jia, R. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/429 · Cited by 4
Swarm Intelligence in Cooperative Environments: Introducing the N-Step Dynamic Tree Search Algorithm
Longa, M. E., İnalhan, G., & Tsourdos, A. (2022) · AIAA SciTech Forum · doi:10.2514/6.2022-1839 · Cited by 5
“There are typically three different branches to approach a learning problem: supervised, unsupervised and reward-based learning methods [1].”
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.