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 301–400 of 1,000
Model-Based Stochastic Search for Large Scale Optimization of Multi-Agent UAV Swarms
Fan, D. D., Theodorou, E. A., & Reeder, J. (2018) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2018.8628677 · Cited by 20
Learning to Communicate via Supervised Attentional Message Processing
Peng, Z., Zhang, L., & Luo, T. (2018) · Computer Animation (CA) · doi:10.1145/3205326.3205346 · Cited by 18
“External communication examples include blackboard, signaling, and message-passing [17].”
BackgroundDistributed cooperative industrial demand response
Allman, A., & Zhang, Q. (2019) · Journal of Process Control · doi:10.1016/j.jprocont.2019.12.011 · Cited by 22
“It is an active field of research and finds wide application in many areas, such as distributed control (Scattolini, 2009; Negenborn and Maestre, 2014), sensor networks (Rabbat and Nowak, 2004; Chen and Sayed, 2012), and machine learning (Panait and Luke, 2005; Boyd et al., 2011).”
BackgroundLarge-Scale Multiagent System Tracking Control Using Mean Field Games
Zhou, Z., & Xu, H. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3071109 · Cited by 23
“For instance, in a vast majority of MAS intelligent control algorithms that feature deep reinforcement learning [17], [18], the finite discrete state space and/or action space have been considered [19], [20].”
BackgroundAn innovative model for describing oil penetration into the doughnut crust during hot air frying
Ghaitaranpour, A., Mohebbi, M., & Koocheki, A. (2021) · Food Research International · doi:10.1016/j.foodres.2021.110458 · Cited by 20
Selecting informative actions improves cooperative multiagent learning
Panait, L., & Luke, S. (2006) · Adaptive Agents and Multi-Agents Systems · doi:10.1145/1160633.1160767 · Cited by 20
“Of particular interest to us is cooperative multiagent learning, where multiple agents learn to work together as a team to accomplish common goals [19].”
BackgroundSelf-citationA Fuzzy Logic based Recommender System for E-Learning System with Multi-Agent Framework
Pandey, H., & Singh, V. K. (2015) · International Journal of Computer Applications · doi:10.5120/21793-5140 · Cited by 20
“LivuiPanait [5] provided a broad survey of the cooperative multi-agent learning literature.”
BackgroundCOOPERATIVE LEARNING IN MULTI-AGENT SYSTEMS FROM INTERMITTENT MEASUREMENTS∗Preprint
Leonard, N. E., Leonard, & Olshevsky, A. (2016) · Cited by 20
Collaborative Visual NavigationPreprint
Wang, H., Wang, W., Zhu, X., Dai, J., & Wang, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.01151 · Cited by 38
“Many other efforts [62, 56, 61] indirectly arrive at cooperation via, for example, policy parameter sharing [29] or experience replay buffer [26].”
Meindl, M., Molinari, F., Lehmann, D., & Seel, T. (2021) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2021.3109646 · Cited by 19
“methods as well as methods based on machine learning [7].”
MethodA study of FMQ heuristic in cooperative multi-agent games.
Matignon, L., Laurent, G. J., & Fort-Piat, N. L. (2008) · HAL · Cited by 18
Analysis and implementation of reinforcement learning on a GNU Radio cognitive radio platform
Ren, Y., Dmochowski, P. A., & Komisarczuk, P. (2010) · International Conference on Cognitive Radio Oriented Wireless Networks (CROWNCOM) · doi:10.4108/icst.crowncom2010.9170 · Cited by 19
A Proximity-Based Q-Learning Reward Function for Femtocell Networks
Tefft, J. R., & Kirsch, N. J. (2013) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2013.6692057 · Cited by 19
“It has been shown that the independent, multi-agent QL approach converges appropriately in many cases [10].”
BackgroundLearning from others: Exchange of classification rules in intelligent distributed systems
Fisch, D., Jänicke, M., Kalkowski, E., & Sick, B. (2012) · Artificial Intelligence · doi:10.1016/j.artint.2012.04.002 · Cited by 24
Multiagent Learning on Traffic Lights Control: Effects of Using Shared Information
de Oliveira, D., & Bazzan, A. L. C. (2009) · Advances in mechatronics and mechanical engineering (AMME) book series · doi:10.4018/978-1-60566-226-8.ch015 · Cited by 20
Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients
Hennes, D., Morrill, D., Omidshafiei, S., Munos, R., Pérolat, J., Lanctot, M., Gruslys, A., Lespiau, J.-B., Parmas, P., Duéñez‐Guzmán, E. A., et al. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/gjmw6851 · Cited by 80
“The problem of multiagent reinforcement learning (MARL) [15, 54, 72], which involves several agents acting and learning simultaneously, is significantly more challenging because each agent perceives its environment as nonstationary [45, 72].”
Optimizing Techniques for Parallel Digital Logic Simulation
Meraji, S., & Tropper, C. (2011) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2011.246 · Cited by 19
“Using PComp and PComm, PLoad of the processor is computed using (1).”
MethodEffective tag mechanisms for evolving coordination
Matlock, M. K., & Sen, S. (2007) · Adaptive Agents and Multi-Agents Systems · doi:10.1145/1329125.1329429 · Cited by 21
“Most of the research on learning in agents and multiagent systems involves learning to interact effectively with another agent [21, 33].”
Autonomous Multiagent Space Exploration with High-Level Human Feedback
Colby, M. K., Yliniemi, L., & Tumer, K. (2016) · Journal of Aerospace Information Systems · doi:10.2514/1.i010379 · Cited by 21
“Thus, assessing the fitness of each agent is context-sensitive and subjective [34].”
BackgroundReward Design in Cooperative Multi-agent Reinforcement Learning for Packet RoutingPreprint
Mao, H., Gong, Z., & Xiao, Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03433 · Cited by 26
“In fact, not all environments can directly calculate the local reward or global reward, as Panait & Luke (2005) point out.”
BackgroundOgunsina, K., & DeLaurentis, D. A. (2021) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104600 · Cited by 25
Ertel, W. (2011) · Undergraduate topics in computer science · doi:10.1007/978-0-85729-299-5_10 · Cited by 19
Limiting Dynamics for Q‐Learning with Memory One in Symmetric Two‐Player, Two‐Action Games
Meylahn, J. M., & Janssen, L. (2021) · Complexity · doi:10.1155/2022/4830491 · Cited by 16
Co-evolutionary dynamics in optimal multi-agent game with environment feedback
Han, W., Zhang, Z., Zhu, Y., & Xia, C. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127510 · Cited by 23
Structural Self-organized Holonic Multi-Agent Manufacturing Systems
Barbosa, J., Leitão, P., Adam, E., & Trentesaux, D. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40090-2_6 · Cited by 18
“Other issues are related to the fact that multi-agent systems are typically deployed into dynamic environments and with problem decomposition to reduce complexity [10].”
BackgroundAchieving Socially Optimal Outcomes in Multiagent Systems with Reinforcement Social Learning
Hao, J., & Leung, H.-F. (2013) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/2517329 · Cited by 18
“Multiagent learning has been proved to be a promising and effective approach to allow the agents to coordinate their actions on optimal outcomes through repeated interactions [Hoen et al. 2005; Panait and Luke 2005].”
BackgroundApplying Bayesian learning to multi-robot patrol
Portugal, D., Couceiro, M. S., & Rocha, R. P. (2013) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2013.6719325 · Cited by 18
“In general, reward-based learning methods are attractive since agents are programmed through reward and punishments without explicitly specifying how the task is to be achieved [16].”
BackgroundImplicit adaptive multi-robot coordination in dynamic environments
Colby, M. K., Chung, J. J., & Tumer, K. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354105 · Cited by 18
“However, in a CCEA, all the agents in the team affect the overall system performance; this means that the fitness of a robot’s policy is based on its interactions with all other robots it collaborates with, resulting in context-dependent and subjective fitness assignment [11].”
BackgroundDifferentially private objective functions in distributed cloud-based optimization
Wang, Y., Hale, M., Egerstedt, M., & Dullerud, G. E. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798824 · Cited by 20
“Applications that make use of distribution optimization include power systems [2], [3], communications [4], [5], [6], signal processing [7], [8], sensor networks [9], [10], and machine learning [11], [12].”
BackgroundChen, B., Song, S., Lipson, H., & Vondrick, C. (2020) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00269 · Cited by 25
A federated society of bots for smart contract testing
Viglianisi, E., Ceccato, M., & Tonella, P. (2020) · Journal of Systems and Software · doi:10.1016/j.jss.2020.110647 · Cited by 20
Multi-agent Systems for Distributed Data Mining Techniques: An Overview
Qasem, M. H., Hudaib, A. A., Obeid, N., Almaiah, M. A., Almomani, O., & Al-Khasawneh, A. M. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-87954-9_3 · Cited by 20
Agent-Based Distributed Data Mining: A Survey
Moemeng, C., Gorodetsky, V., Zuo, Z., Yong, Y., & Chengqi Zhang, B. (2009) · Springer eBooks · doi:10.1007/978-1-4419-0522-2_3 · Cited by 18
“A survey on agent technology for data mining can be found in [ 33 ] . [12] is one of the first works attracting attention to ADDM arguing its advantages in mining vast amount of data stored in network and using collaborative capabilities of DM agents.”
BackgroundCosts and benefits of behavioral specialization
Brutschy, A., Tran, N.-L., Baiboun, N., Frison, M., Pini, G., Roli, A., Dorigo, M., & Birattari, M. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.05.018 · Cited by 18
Kaisers, M., & Tuyls, K. (2011) · Cited by 18
Space-Time Continuous Models of Swarm Robotic Systems: Supporting Global-to-Local Programming
Hamann, H. (2008) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000009904 · Cited by 23
Garattoni, L., & Birattari, M. (2016) · Wiley eBooks · doi:10.1002/047134608x.w8312 · Cited by 26
Chemotaxis emerges as the optimal solution to cooperative search games
Pezzotta, A., Adorisio, M., & Celani, A. (2018) · Physical Review E · doi:10.1103/physreve.98.042401 · Cited by 17
New Approach for Advanced Cooperative Learning Algorithms using RL Methods (ACLA)
Vidhate, D. A., & Kulkarni, P. A. (2016) · International Symposium on Computer Vision and the Internet (VisionNet) · doi:10.1145/2983402.2983411 · Cited by 17
“After each cooperation step the Q-tables of the agents become equivalent[6][7][8].”
MethodInnovative Approach Towards Cooperation Models for Multi-agent Reinforcement Learning (CMMARL)
Vidhate, D. A., & Kulkarni, P. A. (2016) · Communications in computer and information science · doi:10.1007/978-981-10-3433-6_56 · Cited by 17
Enhanced Cooperative Multi-agent Learning Algorithms (ECMLA) using Reinforcement Learning
Vidhate, D. A., & Kulkarni, P. A. (2016) · International Conference on Computing, Analytics and Security Trends · doi:10.1109/cast.2016.7915030 · Cited by 17
A Systematic State-of-the-Art Analysis of Multi-Agent Intrusion Detection
Saeed, I. A., Selamat, A., Rohani, M. F., Krejcar, O., & Chaudhry, J. A. (2020) · IEEE Access · doi:10.1109/access.2020.3027463 · Cited by 17
“Cooperative agents have different beliefs and reasoning methods, and they share a common goal, while collaborative agents share a common objective but keep their individual goals [41].”
BackgroundMethodInfluentialAdami, C., Bryson, D., Offria, C., & Pennock, R. T. (2012) · Cited by 17
Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II
Yliniemi, L., & Tumer, K. (2016) · Soft Computing · doi:10.1007/s00500-016-2124-z · Cited by 20
“This can be due to the agents learning to take a conservative strategy, being able to cooperate with a broader range of teammates (Panait 2010; Panait and Luke 2005) instead of seeking optimal policies.”
BackgroundReinforcement Learning for Mean-Field Game
Agarwal, M., Aggarwal, V., Ghosh, A., & Tiwari, N. (2022) · Algorithms · doi:10.3390/a15030073 · Cited by 17
Sharing in teams of heterogeneous, collaborative learning agents
Gifford, C. M., & Agah, A. (2008) · International Journal of Intelligent Systems · doi:10.1002/int.20331 · Cited by 18
A Brief Introduction to Agents
Shehory, O. M., & Sturm, A. (2014) · Springer eBooks · doi:10.1007/978-3-642-54432-3_1 · Cited by 17
Learning to intercept opponents in first person shooter games
Tastan, B., Chang, Y., & Sukthankar, G. (2012) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2012.6374144 · Cited by 19
“Furthermore there are some cases where it is useful to be able to predict future movement of the player even when the current state is wholly observable, such as the archetypical predator-prey game [3].”
BackgroundTransfer Learning for Multiagent Reinforcement Learning Systems
da Silva, F. L., & Costa, A. H. R. (2021) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s01091ed1v01y202104aim049 · Cited by 24
Qu, S., Wang, J., & Jasperneite, J. (2018) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2018.8502508 · Cited by 21
“The multi-agent reinforcement learning method (MARL)[23] uses all local tasks information, and outputs all value functions of the local task.”
MethodHigh Altitude Platform Station (HAPS) Assisted Computing for Intelligent Transportation Systems
Ren, Q., Abbasi, O., Kurt, G. K., Yanıkömeroğlu, H., & Chen, J. (2021) · Globecom · doi:10.1109/globecom46510.2021.9685074 · Cited by 22
“In this work, we consider the proposed architecture as a cooperative MARL problem where agents are independent decision-makers who coordinate their actions and work together to achieve a shared team reward accumulated over time [8].”
BackgroundMultilevel Relationship Algorithm for Association Rule Mining used for Cooperative Learning
AVidhate, D., & Kulkarni, P. A. (2014) · International Journal of Computer Applications · doi:10.5120/14973-3169 · Cited by 16
Kaiser, T. K., & Hamann, H. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3181004 · Cited by 24
“Forthispurpose,methodsofmachinelearningcanbeused[5], butresearchersmostfrequentlyrelyonmethodsofevolutionary robotics[6]–[8].”
Gradient Play in Stochastic Games: Stationary Points, Convergence, and Sample Complexity
Zhang, R. C., Ren, Z., & Li, N. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3387208 · Cited by 85
“Next, we study a special class of SGs called Markov potential games (MPGs) [29], [30], [31], which includes identical reward multiagent RL [32], [33], [34], [35], [36], [37] as an important special case.”
MethodLearning from demonstration with swarm hierarchies
Sullivan, K. M., & Luke, S. (2012) · Adaptive Agents and Multi-Agents Systems · doi:10.5555/2343576.2343604 · Cited by 16
“Performance”
Self-citationActive visual sensing and collaboration on mobile robots using hierarchical POMDPs
Zhang, S., & Sridharan, M. (2012) · doi:10.5555/2343576.2343602 · Cited by 16
Optimal Experiment Design for Coevolutionary Active Learning
Ly, D., & Lipson, H. (2013) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2013.2281529 · Cited by 18
“Furthermore, coevolutionary active learning is often found in multiagent systems; a survey that includes summaries of numerous applications can be found in [14].”
BackgroundBucur, D., Iacca, G., Gaudesi, M., Squillero, G., & Tonda, A. P. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.11.024 · Cited by 16
“In the last decade, the CCE popularity further boasted due to robotics applications where teams of robots can be asked to perform collective tasks [26].”
BackgroundDesign and implementation of an intelligent product agent architecture in manufacturing systems
Kovalenko, I., Barton, K. L., & Tilbury, D. M. (2017) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa.2017.8247652 · Cited by 20
“In the multi-agent environment, each agent must be autonomous and communicative, while having only a limited, local view of the global system [4].”
BackgroundEvaluation Mechanism of Collective Intelligence for Heterogeneous Agents Group
Dai, A., Zhao, Z., Li, R., Zhang, H., & Zhou, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2971278 · Cited by 18
Ghaitaranpour, A., Mohebbi, M., Koocheki, A., & Ngadi, M. O. (2020) · Innovative Food Science & Emerging Technologies · doi:10.1016/j.ifset.2020.102335 · Cited by 16
hammer: Multi-level coordination of reinforcement learning agents via learned messaging
Gupta, N., Srinivasaraghavan, G., Mohalik, S. K., Kumar, N., & Taylor, M. E. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09096-6 · Cited by 30
“COMA [9] used a centralized critic to estimate the Q-function along with a counterfactual advantage for the decentralized actors in MARL.”
BackgroundInfluentialLearning to cooperate in the Iterated Prisoner’s Dilemma by means of social attachments
Bazzan, A. L. C., Peleteiro, A. M., & Burguillo, J. C. (2011) · Journal of the Brazilian Computer Society · doi:10.1007/s13173-011-0038-2 · Cited by 16
“Since a comprehensive discussion is not possible here, we refer the reader to [26, 31] and references therein.”
Self-coordination of parameter conflicts in D-SON architectures: a Markov decision process framework
Moysen, J., & Giupponi, L. (2015) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-015-0312-7 · Cited by 17
Zhang, Y., & Xie, Y. (2007) · Texas A&M University eBooks · Cited by 16
Development and Evaluation of a Multi-Agent Based Neuro-Fuzzy Arterial Traffic Signal Control System
Zhang, Y., Xie, Y., & Ye, Z. (2007) · Cited by 17
Using Meta-Agents for Multi-Agents in Networks
Håkansson, A., & Hartung, R. (2007) · International Conference on Artificial Intelligence · Cited by 16
Mechanisms for norm emergence and norm identification in multi-agent societies
Tony, B., & Savarimuthu, B. T. R. (2011) · Otago University Research Archive (University of Otago) · Cited by 22
Attend2Pack: Bin Packing through Deep Reinforcement Learning with AttentionPreprint
Zhang, J., Zi, B., & Ge, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04333 · Cited by 47
“This decomposition can be regarded as casting the full joint combinatorial action space among two agents, formulating BPP as a fully-cooperative multi-agent reinforcement learning task (Panait & Luke, 2005; Busoniu et al., 2008).”
Machine Learning for Aggregate Computing: a Research Roadmap
Aguzzi, G., Casadei, R., & Viroli, M. (2022) · IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW) · doi:10.1109/icdcsw56584.2022.00032 · Cited by 17
“A recurrent solution in MARL for such kind of situation is to consider the agents’ policies homogeneous [37] in order to drastically reduce the policy search space.”
BackgroundPersonal sustained cooperation based on networked evolutionary game theory
Yan, J. (2023) · Scientific Reports · doi:10.1038/s41598-023-36318-7 · Cited by 18
Personas-based Student Grouping using reinforcement learning and linear programming
Ma, S., Luo, Y., & Yang, Y. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111071 · Cited by 22
Zhao, Z., Ding, J., Zhang, J., Shi, Y., & Chai, T. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2024.3432817 · Cited by 15
“Digital Object Identifier 10.1109/TCNS.2024.3432817 are more robust, flexible, and scalable and have been successfully applied to robotic systems [4], sensor networks [5], and machine learning [6], just to name a few.”
InfluentialHuang, C., Liao, J., Shen, H., Aye, N. N., Wang, Y., Chen, H., Yang, D., Luo, Y., & Chuang, Y. (2009) · Computer Applications in Engineering Education · doi:10.1002/cae.20359 · Cited by 15
Cooperative Coevolution of Partially Heterogeneous Multiagent Systems
Gomes, J., Mariano, P., & Christensen, A. L. (2015) · Repositório do ISCTE-IUL · doi:10.5555/2772879.2772919 · Cited by 15
Learning Agent for a Service-Oriented Context-Aware Recommender System in Heterogeneous Environment.
Nawrocki, P., Śnieżyński, B., & Czyżewski, J. (2016) · Cited by 15
Distribution Transformer Condition Monitoring based on Edge Intelligence for Industrial IoT
Thangiah, L., Ramanathan, C., & Chodisetty, L. S. (2019) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot.2019.8767272 · Cited by 16
“In future, we plan to carry out comprehensive experiments involving cooperative learning by enabling peer-peer communication between the agents and backend analytics to evaluate the implications of various nonfunctional requirements such as scalability, fault-tolerance and security [1][4][7][8].”
BackgroundMethodEntropy regularized actor-critic based multi-agent deep reinforcement learning for stochastic games
Hao, D., Zhang, D., Shi, Q., & Li, K. (2022) · Information Sciences · doi:10.1016/j.ins.2022.10.022 · Cited by 16
Makino, T., & Aihara, K. (2006) · Adaptive Agents and Multi-Agents Systems · doi:10.1145/1160633.1160772 · Cited by 15
Improving the Efficiency of Self-Organizing Emergent Systems by an Advisor
Steghöfer, J.-P., Denzinger, J., Kasinger, H., & Bauer, B. (2010) · IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe) · doi:10.1109/ease.2010.16 · Cited by 15
“Although learning of behavior is a technique widely applied in MASs (see [22] for an overview), the emphasis in this field is on learning complete behaviors, usually for achieving one specific goal but not many constantly changing goals.”
MethodÜre, N. K., Omidshafiei, S., Lopez, B. T., Agha–mohammadi, A., How, J. P., & Vian, J. L. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354107 · Cited by 14
“Many planning algorithms utilize a model of the mission dynamics to perform lookahead and compute policies, however such models may not exist beforehand and/or might be incomplete [3].”
BackgroundMethodAn ontologist feedback driven ontology evolution with an adaptive multi-agent system
Benomrane, S., Sellami, Z., & Ayed, M. B. (2016) · Advanced Engineering Informatics · doi:10.1016/j.aei.2016.05.002 · Cited by 15
Combining reward shaping and hierarchies for scaling to large multiagent systems
HolmesParker, C., Agogino, A., & Tumer, K. (2016) · The Knowledge Engineering Review · doi:10.1017/s0269888915000156 · Cited by 17
Rendezvous planning for multiple autonomous underwater vehicles using a Markov decision process
Yordanova, V., Griffiths, H., & Hailes, S. M. V. (2017) · IET Radar Sonar & Navigation · doi:10.1049/iet-rsn.2017.0098 · Cited by 15
“Reducing the complexity of an MDP model and creating a manageable state and action space is a well known problem and has been described in [16].”
BackgroundLearning to Act in Decentralized Partially Observable MDPs
Dibangoye, J., & Buffet, O. (2018) · HAL · Cited by 16
Development of a distributed multi-agent system monitoring and control networks of 0.4–35 kV
Zelenskii, E., Kononov, Y. G., Федоренко, В. В., Михайлович, В. А., & Samoylenko, V. (2017) · International Conference on Control in Technical Systems (CTS) · doi:10.1109/ctsys.2017.8109543 · Cited by 14
Comparing Statistical, Analytical, and Learning-Based Routing Approaches for Delay-Tolerant Networks
D’Argenio, P. R., Fraire, J. A., Hartmanns, A., & Raverta, F. D. (2024) · ACM Transactions on Modeling and Computer Simulation · doi:10.1145/3665927 · Cited by 17
“One straightforward adaptation of Q-learning to the multi-agent local-information setting is the concurrent learning approach [66].”
Fernández-León, J. A., Acosta, G. G., & Rozenfeld, A. (2014) · Biosystems · doi:10.1016/j.biosystems.2014.08.003 · Cited by 14
Enhancing the Adaptation of BDI Agents Using Learning Techniques
Airiau, S., Padgham, L., Sardiña, S., & Sen, S. (2009) · International Journal of Agent Technologies and Systems · doi:10.4018/jats.2009040101 · Cited by 14
“multiagent learning (Alonso, d’Inverno, Kudenko, Luck, & J.Noble, 2001, Panait & Luke, 2005,”
BackgroundWang, H., & Song, R. (2012) · Wireless Personal Communications · doi:10.1007/s11277-012-0950-6 · Cited by 14
“Although the optimal evidence for convergence is not rigid, it has already been verified convergent in [25].”
BackgroundJREP: Extending Repast Simphony for JADE Agent Behavior Components
Görmer, J., Homoceanu, G., Mumme, C., Huhn, M., & Müller, J. P. (2011) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat.2011.120 · Cited by 14
“Multi-agent systems (MAS) [10] are a promising paradigm for constructing complex software-intensive systems providing multiple methods for modeling and simulating.”
BackgroundInfluentialSelf-organization for scheduling in agile manufacturing
Madureira, A. M., Pereira, I. F., & Sousa, N. (2011) · IEEE International Conference on Cybernetic Intelligent Systems (CIS) · doi:10.1109/cis.2011.6169132 · Cited by 14
“The interest and research on DSS exhibiting self-* properties is increasingly drawing to formalize some of the ideas from Autonomic Oriented Computing for handling problems in complex manufacturing systems and to identify mechanism that makes use of autonomous entities in solving hard computational…”
BackgroundIdentikit of modifiable vehicles at Virtual Semantic Environment
Abrosimov, V., Ryvkin, S. E., Goncharenko, V. I., Rozhnov, A. V., & Александрович, Л. И. (2017) · International Aegean Conference on Electrical Machines and Power Electronics & International Conference on Optimization of Electrical and Electronic Equipment (ACEMP-OPTIM) · doi:10.1109/optim.2017.7975085 · Cited by 14
Distributed Strategy Adaptation with a Prediction Function in Multi-Agent Task Allocation
Turner, J., Meng, Q., Schaefer, G., & Soltoggio, A. (2018) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/wfxh7138 · Cited by 22
“Panait and Luke [21] provide a comprehensive survey of MARL, as well as evolutionary learning, for cooperative teams.”
Graves, R., Nelson, Z. E., & Chakraborty, S. (2021) · Journal of Intelligent Transportation Systems · doi:10.1080/15472450.2021.2016405 · Cited by 14
“This thrust to leverage new computing technology to control traffic signal networks has been well cataloged by several groups which give overviews of RL, MAL, and general AI-based solutions for signal timing (Bazzan, 2009; Panait and Luke, 2005; Yau et al., 2017; Zhao et al., 2011).”
BackgroundModeling Human Behavior in Cyber-Physical-Social Infrastructure Systems
Doctorarastoo, M., Flanigan, K. A., Berges, M. E., & McComb, C. (2023) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/3600100.3626338 · Cited by 19
“For each human agent 𝑛 and specific activity 𝑗 , a unique subpolicy, denoted as 𝜋 LO ,𝑗 in Figure 1, is trained using MARL [15, 19].”
Intelligent decision support for Marine safety and Security Operations
Glässer, U., Jackson, P. J., Araghi, A. K., & Shahir, H. Y. (2010) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi.2010.5484769 · Cited by 16
MALEF: Framework for distributed machine learning and data mining
Tožička, J., Rovatsos, M., Pěchouček, M., & Urban, S. (2008) · International Journal of Intelligent Information and Database Systems · doi:10.1504/ijiids.2008.017242 · Cited by 14
“The key difference between this kind of collaborative agent-based learning systems (Panait and Luke, 2005) and our own framework is that these approaches assume a joint learning goal that is pursued collaboratively by all agents.”
Moise, G., Vlădoiu, M., & Constantinescu, Z. (2013) · Studies in computational intelligence · doi:10.1007/978-3-642-41965-2_7 · Cited by 14
“These constraints are essential to the definition of a real multiagent system [74].”
BackgroundCan bounded and self-interested agents be teammates? Application to planning in ad hoc teams
Chandrasekaran, M., Doshi, P., Zeng, Y., & Chen, Y. (2016) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-016-9354-4 · Cited by 14
“Integrating learning while planning provides a middle ground (or a bridge) between multiagent planning frameworks such as DEC-POMDPs and joint learning for cooperative domains [58].”
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.