25,121 Hits in 5.4 sec

An adaptive-learning framework for semi-cooperative multi-agent coordination

Abdeslem Boukhtouta, Jean Berger, Warren B. Powell, Abraham George
2011 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)  
In this research, we develop a general mathematical model for distributed, semi-cooperative planning and suggest a solution strategy which involves decomposing the system into subproblems, each of which  ...  is specified at a certain period in time and controlled by an agent.  ...  We develop a general, mathematical model of a multi-agent system for distributed, semi-cooperative planning, building on the DRTP modeling framework. 2.)  ... 
doi:10.1109/adprl.2011.5967386 dblp:conf/adprl/BoukhtoutaBPG11 fatcat:fbao2h32rrd3zleprs4qqdqp5q

Evolution of Cooperative Hunting in Artificial Multi-layered Societies [article]

Honglin Bao, Wolfgang Banzhaf
2021 arXiv   pre-print
In this paper, an agent-based model is proposed to study the evolution of cooperative hunting behaviors in an artificial society.  ...  Experiments are carried out to test the evolution of cooperation in this closed-loop semi-supervised emergent system with different parameters.  ...  In this paper, based on an evolutionary game theoretical framework, we extend it with multi-agent reinforcement learning to investigate the mechanisms behind the cooperative hunting phenomena in social  ... 
arXiv:2005.11580v5 fatcat:kcicqntdfzegjjg64zulxi5ylm

Human-Robot Teams in Entertainment and Other Everyday Scenarios [article]

Pooyan Fazli, Alan K. Mackworth
2009 arXiv   pre-print
In this paper, we focus upon problem domains and tasks in which multiple robots, humans and other agents are cooperating through coordination to satisfy a set of goals or to maximize utility.  ...  We discuss the teamwork problem and propose an architecture to address this.  ...  Multi-agent planning coordinates the actions of multiple agents to achieve a goal [14] .  ... 
arXiv:0908.2661v1 fatcat:v5phwpiuf5ccddod6mbnovtpdi

Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients [article]

Bozhidar Vasilev, Tarun Gupta, Bei Peng, Shimon Whiteson
2021 arXiv   pre-print
Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios.  ...  In this paper, we introduce semi-on-policy (SOP) training as an effective and computationally efficient way to address the sample inefficiency of on-policy policy gradient methods.  ...  QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Safe and Efficient Off-Policy Reinforcement Learning.  ... 
arXiv:2104.13446v2 fatcat:aat2z6j7azcaxlqx5tnpwoxyje

Drone-Assisted Cellular Networks: A Multi-Agent Reinforcement Learning Approach

Seif Eddine Hammami, Hossam Afifi, Hassine Moungla, Ahmed Kamel
2019 ICC 2019 - 2019 IEEE International Conference on Communications (ICC)  
Drone-assisted cellular networks: a multi-agent reinforcement learning approach.  ...  We propose in this paper, a multiagent reinforcement learning approach for dynamic drones-cells management. Our approach is based on an enhanced joint action selection.  ...  reinforcement learning model is based on a semi-centralized cooperative solution.  ... 
doi:10.1109/icc.2019.8762079 dblp:conf/icc/HammamiAMK19 fatcat:iu5jowqrrjgrph4iuioiogpfhu

Hierarchical multi-agent reinforcement learning

Mohammad Ghavamzadeh, Sridhar Mahadevan, Rajbala Makar
2006 Autonomous Agents and Multi-Agent Systems  
We introduce a hierarchical multi-agent reinforcement learning (RL) framework, and propose a hierarchical multi-agent RL algorithm called Cooperative HRL.  ...  We extend the multi-agent HRL framework to include communication decisions and propose a cooperative multi-agent HRL algorithm called COM-Cooperative HRL.  ...  Acknowledgements The first author would like to thank Balaraman Ravindran for his useful comments.  ... 
doi:10.1007/s10458-006-7035-4 fatcat:7qyhm7mzfbgb5mkhwebz4oeehu

Hierarchical multi-agent reinforcement learning

Rajbala Makar, Sridhar Mahadevan, Mohammad Ghavamzadeh
2001 Proceedings of the fifth international conference on Autonomous agents - AGENTS '01  
We introduce a hierarchical multi-agent reinforcement learning (RL) framework, and propose a hierarchical multi-agent RL algorithm called Cooperative HRL.  ...  We extend the multi-agent HRL framework to include communication decisions and propose a cooperative multi-agent HRL algorithm called COM-Cooperative HRL.  ...  Acknowledgements The first author would like to thank Balaraman Ravindran for his useful comments.  ... 
doi:10.1145/375735.376302 dblp:conf/agents/MakarMG01 fatcat:4s256e3aa5frvgbczyisddr5ja


Akash Agrawal, Sung Jun Won, Tushar Sharma, Mayuri Deshpande, Christopher McComb
2021 Proceedings of the Design Society  
We specifically propose a multi-agent framework involving mobile robots, machines, humans.  ...  This work offers a standardizing framework for integrated job scheduling and navigation control in an autonomous mobile robot driven shop floor, an increasingly common IM paradigm.  ...  MULTI-AGENT FRAMEWORK FOR MOBILE ROBOT DRIVEN SHOP FLOOR We propose a multi-agent framework for an autonomous mobile robot driven shop floor, wherein the sensory, control, and communication protocols have  ... 
doi:10.1017/pds.2021.17 fatcat:bjoy4jmoaffwvdundqzi3b4e5e

Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks [article]

Jing Xu, Fangwei Zhong, Yizhou Wang
2020 arXiv   pre-print
To realize this, we propose a Hierarchical Target-oriented Multi-Agent Coordination (HiT-MAC), which decomposes the target coverage problem into two-level tasks: targets assignment by a coordinator and  ...  We also conduct an ablative analysis on the effectiveness of the introduced components in the framework.  ...  Xiaotie Deng for their helpful discussion in our early work.  ... 
arXiv:2010.13110v1 fatcat:rlrqrjt76vaqpmebwrmn5oiyka

Multi-level Frontier based Topic-specific Crawler Design with Improved URL Ordering

Akilandeswari Jeyapal, Gopalan Palanisamy
2008 Computer and Information Science  
Coordinator agent is responsible for disseminating URLs from crawling frontiers to individual retrieval agents.  ...  In this paper, a novel design of a topic specific web crawler based on multi-agent system is presented. The architecture proposed employs two types of agents: retrieval and coordinator agents.  ...  In this paper, an architectural framework is presented for crawling topic specific Web pages using multi-agent based system.  ... 
doi:10.5539/cis.v1n4p99 fatcat:hafin6mrirb2nmfrl73ifm6wsu

Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems [article]

Amanda Prorok, Matthew Malencia, Luca Carlone, Gaurav S. Sukhatme, Brian M. Sadler, Vijay Kumar
2021 arXiv   pre-print
In this survey article, we analyze how resilience is achieved in networks of agents and multi-robot systems that are able to overcome adversity by leveraging system-wide complementarity, diversity, and  ...  We address these questions across foundational robotics domains, spanning perception, control, planning, and learning.  ...  GNNs): While centralizedtraining, decentralized-execution (CTDE) [243] is the typical paradigm for multi-agent RL and multi-agent IL, the underlying machine learning framework can vary.  ... 
arXiv:2109.12343v1 fatcat:vxt62eluljfelcifzdlosv34cq

Evaluating semi-cooperative Nash/Stackelberg Q-learning for traffic routes plan in a single intersection

Jian Guo, Istvan Harmati
2020 Control Engineering Practice  
, with combining game theory and RL in decision-making in the multi-agent framework.  ...  Then an extended version called semi-cooperative Stackelberg Q-learning is designed to make a comparison, where Nash equilibrium is replaced by Stackelberg equilibrium in the Q-learning process.  ...  A multi-agent reinforcement learning coordination method can handle coordination problems in continuous action cooperative Markov games effectively (Zhang, Li, Hao, Chen, Tuyls et al., 2018) .  ... 
doi:10.1016/j.conengprac.2020.104525 fatcat:weu5ra2gvjanpkp3riqu6zrsxe

IJIMAI Editor�s Note - Vol. 2 Issue 4

Rub�n Gonzalez-Crespo
2013 International Journal of Interactive Multimedia and Artificial Intelligence  
Results confirm the usefulness of the analysis tools when exporting to Cooperative Multi-agent Systems that use different configurations.  ...  López et al. presents the progress and final state of CAIN-21, an extensible and metadata driven multimedia adaptation in the MPEG-21 framework.  ... 
doi:10.9781/ijimai.2013.240 fatcat:bvd67cuz4zbejg75b6tg4j5mwy

Understanding Behavior of System of Systems Through Computational Intelligence Techniques

Cihan Dagli, Nil Kilicay
2007 2007 1st Annual IEEE Systems Conference  
The semi-Therefore, the need to focus on overall system autonomous systems (people, organizations) are behavior is becoming an unavoidable issue. integrated through cooperative arrangements.  ...  The world is facing an increasing the application area and focus [2], [11] , level of systems integration leading towards [14] .Future Combat Systems (FCS), NATO, trans-Systems of Systems (SoS) that adapt  ...  Agents in memory. The long-term production memory Multi-agent systems (MAS) contain processes for coordinates all the modules in ACR-R [9] .  ... 
doi:10.1109/systems.2007.374658 fatcat:e7n524nxr5df5pnuied5ciagny

Multi-agent Hierarchical Reinforcement Learning with Dynamic Termination [chapter]

Dongge Han, Wendelin Böhmer, Michael Wooldridge, Alex Rogers
2019 Lecture Notes in Computer Science  
One obvious possibility is for each agent to broadcast their current intention, for example, the currently executed option in a hierarchical reinforcement learning framework.  ...  We evaluate our model empirically on a set of multi-agent pursuit and taxi tasks, and show that our agents learn to adapt flexibly across scenarios that require different termination behaviours.  ...  Method In this section we will present our framework for deep decentralized hierarchical multi-agent Q-learning.  ... 
doi:10.1007/978-3-030-29911-8_7 fatcat:uegmi357ynd7po47m25o5htybm
« Previous Showing results 1 — 15 out of 25,121 results