294 Hits in 6.6 sec


Peter Stone, Manuela Veloso
2012 Autonomous Robots  
When several different systems exist that could illustrate the same or similar MAS techniques, the systems presented here are biased towards those that use machine learning (ML) approaches.  ...  To mention just one of the many exciting successes, a car recently steered itself more than 95% of the way across the United States using the ALVINN system [60] .  ...  Acknowledgements We would like to thank Keith Decker  ... 
doi:10.1023/a:1008942012299 fatcat:4tjofcxn4jdkdn5ey7oe2oi2xm

Adaptive learning: A new decentralized reinforcement learning approach for cooperative multiagent systems

Li Meng-Lin, Chen Shao-Fei, Chen Jing
2020 IEEE Access  
This paper focuses on how independent learners (ILs, structures used in decentralized reinforcement learning) decide on their individual behaviors to achieve coherent joint behavior.  ...  Our work provides a new way to solve the miscoordination problem for reinforcement learning algorithms in the scale of dozens or more number of agents.  ...  Based on the current research, multiagent reinforcement learning algorithms still face the following key problems: i) In a multiagent environment with heterogeneous agents, the existence of an optimal  ... 
doi:10.1109/access.2020.2997899 fatcat:nyhq2q6u5jhrpknp634xro3wja

Scalable multiagent learning through indirect encoding of policy geometry

David B. D'Ambrosio, Kenneth O. Stanley
2013 Evolutionary Intelligence  
This paper presents an alternative approach to multiagent learning called multiagent HyperNEAT that represents the team as a pattern of policies rather than as a set of individual agents.  ...  While there are a variety of traditional approaches to multiagent learning, many suffer from increased computational costs for large teams and the problem of reinvention (that is, the inability to recognize  ...  Cooperative Multiagent Learning Multiagent systems confront a broad range of domains, creating the opportunity for real-world applications such as room clearing, pursuit [27] , and synchronized motion  ... 
doi:10.1007/s12065-012-0086-3 fatcat:7ropvv3r5nemlh4hkliqeymqgi

Generative encoding for multiagent learning

David B. D'Ambrosio, Kenneth O. Stanley
2008 Proceedings of the 10th annual conference on Genetic and evolutionary computation - GECCO '08  
For example, a significant problem for multiagent learning is that policies learned separately for different agent roles may nevertheless need to share a basic skill set, forcing the learning algorithm  ...  This paper argues that multiagent learning is a potential "killer application" for generative and developmental systems (GDS) because key challenges in learning to coordinate a team of agents are naturally  ...  Ma-chine learning is an appealing approach to constructing such multiagent systems because the best cooperative team policy may not be known a priori.  ... 
doi:10.1145/1389095.1389256 dblp:conf/gecco/DAmbrosioS08 fatcat:nqvwapuiafg7dijcs6kpvoxetu

Cooperative Multi-agent Control Using Deep Reinforcement Learning [chapter]

Jayesh K. Gupta, Maxim Egorov, Mykel Kochenderfer
2017 Lecture Notes in Computer Science  
Using deep reinforcement learning with a curriculum learning scheme, our approach can solve problems that were previously considered intractable by most multi-agent reinforcement learning algorithms.  ...  We extend three classes of single-agent deep reinforcement learning algorithms based on policy gradient, temporal-difference error, and actor-critic methods to cooperative multi-agent systems.  ...  The authors would like to thank the anonymous reviewers for their helpful comments.  ... 
doi:10.1007/978-3-319-71682-4_5 fatcat:ie4vvneipjgxbdwngj3bncs6eu

Can good learners always compensate for poor learners?

Keith Sullivan, Liviu Panait, Gabriel Balan, Sean Luke
2006 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems - AAMAS '06  
Previous work has given an example where a special learning algorithm (FMQ) is capable of doing just that when paired with a specific less capable algorithm even in games which stump the poorer algorithm  ...  We give a straightforward extension to the coordination game in which FMQ cannot compensate for the lesser algorithm.  ...  We are aware of only one paper that focuses on concurrent heterogeneous cooperative learners: [11] analyze different combinations of a traditional reinforcement learning algorithm and an extension called  ... 
doi:10.1145/1160633.1160777 dblp:conf/atal/SullivanPBL06 fatcat:ozlb5yo2zbedhbspaeknsajaze

A New Decentralized Approach of Multiagent Cooperative Pursuit Based on the Iterated Elimination of Dominated Strategies Model

Mohammed El Habib Souidi, Songhao Piao
2016 Mathematical Problems in Engineering  
Game Theory is a promising approach to acquire coalition formations in multiagent systems.  ...  This paper is focused on the importance of the distributed computation and the dynamic formation and reformation of pursuit groups in pursuit-evasion problems.  ...  Acknowledgments This paper is supported by National Natural Science Foundation of China (no. 61375081) and a special fund project of Harbin science and technology innovation talents research (no.  ... 
doi:10.1155/2016/5192423 fatcat:jehvdvoeybaofad4dwb2uplxwm

Transfer Learning Method Using Ontology for Heterogeneous Multi-agent Reinforcement Learning

Hitoshi Kono, Akiya Kamimura, Kohji Tomita, Yuta Murata, Tsuyoshi Suzuki
2014 International Journal of Advanced Computer Science and Applications  
This paper presents a framework, called the knowledge co-creation framework (KCF), for heterogeneous multiagent robot systems that use a transfer learning method.  ...  A multiagent robot system (MARS) that utilizes reinforcement learning and a transfer learning method has recently been studied in realworld situations.  ...  ACKNOWLEDGMENT This work was partially supported by the Research Institute for Science and Technology of Tokyo Denki University Grant Number Q14J-01 Japan.  ... 
doi:10.14569/ijacsa.2014.051022 fatcat:iavbukidujayzp3q33izppabr4

Cooperative Multi-Agent Learning: The State of the Art

Liviu Panait, Sean Luke
2005 Autonomous Agents and Multi-Agent Systems  
TEAM LEARNING 4 A standard approach to applying cooperative coevolutionary algorithms (or CCEAs) to an optimization problem starts by decomposing the problem representation into subcomponents, then assigning  ...  To avoid confusion, we use "reward-based learning" for the former, and "reinforcement learning" for latter.  ...  Acknowledgments The  ... 
doi:10.1007/s10458-005-2631-2 fatcat:u3xlftotajfitdtfmvbmggwgbi

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., +, Online Reinforcement Learning Control for the Personalization of a Robotic Knee Prosthesis.  ...  Wang, D., TCYB June 2020 2740-2748 Online Reinforcement Learning Control for the Personalization of a Robotic Knee Prosthesis.  ...  Stock markets A Quantum-Inspired Similarity Measure for the Analysis of Complete Weighted Graphs. Bai, L., +, TCYB March 2020 1264 -1277  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Coevolution of Role-Based Cooperation in Multiagent Systems

C.H. Yong, R. Miikkulainen
2009 IEEE Transactions on Autonomous Mental Development  
In tasks such as pursuit and evasion, multiple agents need to coordinate their behavior to achieve a common goal. An interesting question is, how can such behavior be best evolved?  ...  First, the approach is shown to be more efficient than evolving a single central controller for all agents.  ...  Gomez for suggestions on adapting ESP to multiagent systems, as well as the anonymous reviewers for suggestions on stigmergy and network size experiments.  ... 
doi:10.1109/tamd.2009.2037732 fatcat:gesaiklstfbxxo2wwbeptdv5xu

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Note that the item title is found only under the primary entry in the Author Index.  ...  Distributed Fault-Tolerant Control of Multiagent Systems: An Adaptive Learning Approach.  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

Making Levels More Challenging with a Cooperative Strategy of Ghosts in Pac-Man

Taeyeong Choi, Hyeon-Suk Na
2015 Journal of Korea Game Society  
In this paper, we introduce a cooperative strategy based on the A* algorithm for enemies' AI in the Pac-Man game.  ...  The artificial intelligence (AI) of Non-Player Companions (NPC), especially opponents, is a key element to adjust the level of games in game design.  ...  Kakazu, "An approach to the pursuit problem on a heterogeneous multiagent system using reinforcement learning", Elsevier Journal on Robotics and Autonomous Systems, Vol. 43, No. 4, pp. 245-256, 2003. [  ... 
doi:10.7583/jkgs.2015.15.5.89 fatcat:wdpdxdzohracjmnk7dlcpum47i

Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments [article]

Zhenhui Ye, Xiaohong Jiang, Guanghua Song, Bowei Yang
2021 arXiv   pre-print
Specifically, we construct the multi-agent system as a graph, use the hierarchical graph attention network(HGAT) to achieve communication between neighboring agents, and exploit GRU to enable agents to  ...  Experimental results based on three homogeneous tasks and one heterogeneous environment not only show that our approach achieves clear improvements compared with four baselines, but also demonstrates the  ...  The recent progress of deep learning and graph learning provides a new idea for MARL, i.e., to regard the multiagent system as a graph.  ... 
arXiv:2109.02032v1 fatcat:aks4pnleavdglpcxmny3z2o5um

Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles

Szilard Aradi
2020 IEEE transactions on intelligent transportation systems (Print)  
A wide range of techniques in Machine Learning itself have been developed, and this article describes one of these fields, Deep Reinforcement Learning (DRL).  ...  The main elements of designing such a system are the modeling of the environment, the modeling abstractions, the description of the state and the perception models, the appropriate rewarding, and the realization  ...  ACKNOWLEDGMENT The research reported in this paper and carried out at the Budapest University of Technology and Economics was supported by the "TKP2020, Institutional Excellence Program" of the National  ... 
doi:10.1109/tits.2020.3024655 fatcat:wk4c2ked3jho3jtqdn4o5ys4zu
« Previous Showing results 1 — 15 out of 294 results