Filters








1,215,469 Hits in 1.7 sec

USING REINFORCEMENT LEARNING TO COORDINATE BETTER

Cora B. Excelente-Toledo, Nicholas R. Jennings
2005 Computational intelligence  
Specifically, our motivating hypothesis is that to deal with dynamic and unpredictable environments it is important to have agents that learn the right situations in which to attempt coordination and the  ...  This paper examines the potential and the impact of introducing learning capabilities into autonomous agents that make decisions at run-time about which mechanism to exploit in order to coordinate their  ...  Thus, LODES focuses on "what information to learn" and COLLAGE on "learning the situation where to use a coordination strategy".  ... 
doi:10.1111/j.1467-8640.2005.00272.x fatcat:ivb25j2f7je75pqb7vbjmva4sq

Can we rationally learn to coordinate?

Sanjeev Goyal, Maarten Janssen
1996 Theory and Decision  
In this paper we examine the issue whether individual rationality considerations are sufficient to guarantee that individuals will learn to coordinate.  ...  This conclusion may be seen as supporting the viewpoint of 'institutional individualism' in contrast to 'psychological individualism'.  ...  Crawford and Haller argue that there are optimal rules of learning to coordinate.  ... 
doi:10.1007/bf00133159 fatcat:azbecwerv5funfv4d45tnkmh3a

Learning to select a coordination mechanism

Cora B. Excelente-Toledo, Nicholas R. Jennings
2002 Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 3 - AAMAS '02  
To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior speci£c permission and/or a fee. AAMAS'02, July 15-19, 2002, Bologna, Italy.  ...  ¤ B 4 & ' A C 0 ¦ 2 Y § ¤ 0 ) © G r b © Deciding what to bid to become an AiCoop 3 ¡ ¤ ! © B ' ! @ # $ ¥ $ 4 £ " d ' Y © 8 $ @ A ¤ ¥ $ # # $ & § E © $ # $ £ ¦ 4 £ " § © # $ £ " !  ... 
doi:10.1145/545056.545080 dblp:conf/atal/Excelente-ToledoJ02 fatcat:hd7bciftn5fafkpeydkqnbe37q

Learning to Coordinate in Social Networks

Pooya Molavi, Ceyhun Eksin, Alejandro Ribeiro, Ali Jadbabaie
2016 Operations Research  
The agents thus have the incentive to correctly estimate the state while trying to coordinate with and learn from others.  ...  We study a repeated game in which a group of players attempt to coordinate on a desired, but only partially known, outcome. The desired outcome is represented by an unknown state of the world.  ...  Moreover, oftentimes agents can only communicate with a handful of other agents, while at the same time, trying to coordinate with and learn from everybody else.  ... 
doi:10.1287/opre.2015.1381 fatcat:myh2t2t73rgtpdxes5v6jwkcre

Learning to coordinate in complex networks

Sven Van Segbroeck, Steven de Jong, Ann Nowé, Francisco C Santos, Tom Lenaerts
2010 Adaptive Behavior  
As such, our work provides a clear-cut picture of the learning dynamics associated with networks of agents trying to optimally coordinate their actions.  ...  Here, we address this fundamental problem, both analytically and via computer simulations, examining networks of agents that engage in stag-hunt games with their neighbors and thereby learn to coordinate  ...  We also want to thank Karl Tuyls for reviewing a draft of the manuscript. This research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.  ... 
doi:10.1177/1059712310384282 fatcat:of463gnzpratdjvkoxinmy2vta

Learning to select a coordination mechanism

Cora B. Excelente-Toledo, Nicholas R. Jennings
2002 Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 3 - AAMAS '02  
To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior speci£c permission and/or a fee. AAMAS'02, July 15-19, 2002, Bologna, Italy.  ...  ¤ B 4 & ' A C 0 ¦ 2 Y § ¤ 0 ) © G r b © Deciding what to bid to become an AiCoop 3 ¡ ¤ ! © B ' ! @ # $ ¥ $ 4 £ " d ' Y © 8 $ @ A ¤ ¥ $ # # $ & § E © $ # $ £ ¦ 4 £ " § © # $ £ " !  ... 
doi:10.1145/545079.545080 fatcat:nuntgyltt5haliy2uf7j2bw32y

Learning to Coordinate in Social Networks

Pooya Molavi, Ceyhun Eksin, Alejandro Ribeiro, Ali Jadbabaie
2013 Social Science Research Network  
The agents thus have the incentive to correctly estimate the state while trying to coordinate with and learn from others.  ...  We study a repeated game in which a group of players attempt to coordinate on a desired, but only partially known, outcome. The desired outcome is represented by an unknown state of the world.  ...  Moreover, oftentimes agents can only communicate with a handful of other agents, while at the same time, trying to coordinate with and learn from everybody else.  ... 
doi:10.2139/ssrn.2292124 fatcat:3s47fbx2qncgthddwwpqsbqzpi

Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation [article]

Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita
2018 arXiv   pre-print
We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering.  ...  In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer.  ...  In reinforcement learning efficient exploration is key to achieve good performance.  ... 
arXiv:1809.10658v2 fatcat:toojqgbyinhr7ae63rw6mgmne4

Coordinated Online Learning With Applications to Learning User Preferences [article]

Christoph Hirnschall, Adish Singla, Sebastian Tschiatschek, Andreas Krause
2017 arXiv   pre-print
To exploit this relationship, we design a novel algorithm -- COOL -- for coordinating the individual online learners: Our key idea is to coordinate their parameters via weighted projections onto a convex  ...  We apply our results on the application of learning users' preferences on the Airbnb marketplace with the goal of incentivizing users to explore under-reviewed apartments.  ...  The goal is to learn arXiv:1702.02849v1 [cs.  ... 
arXiv:1702.02849v1 fatcat:7mldwbgn6bfltixrvfv4wge5oi

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games [article]

Peng Peng, Ying Wen, Yaodong Yang, Quan Yuan, Zhenkun Tang, Haitao Long, Jun Wang
2017 arXiv   pre-print
Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI.  ...  In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies.  ...  Through end-to-end learning, our BiCNet would be able to successfully learn several effective coordination strategies.  ... 
arXiv:1703.10069v4 fatcat:2shr545bsnfw7peqn6cawxntsa

Improving Multi-agent Coordination by Learning to Estimate Contention [article]

Panayiotis Danassis, Florian Wiedemair, Boi Faltings
2021 arXiv   pre-print
as a coordination mechanism for each stage game.  ...  ALMA-Learning is decentralized, observes only own action/reward pairs, requires no inter-agent communication, and achieves near-optimal (<5% loss) and fair coordination in a variety of synthetic scenarios  ...  ALMA-Learning ALMA-Learning uses ALMA as a sub-routine, specifically as a coordination mechanism for each stage of the repeated game.  ... 
arXiv:2105.04027v2 fatcat:umzhdt53xjfbjenfp43milruqi

Learning to Mine Chinese Coordinate Terms Using the Web [article]

Xiaojiang Huang, Xiaojun Wan, Jianguo Xiao
2015 arXiv   pre-print
We propose a semi-supervised method that integrates manually defined linguistic patterns and automatically learned semi-structural patterns to extract coordinate terms in Chinese from web search results  ...  Coordinate relation refers to the relation between instances of a concept and the relation between the directly hyponyms of a concept.  ...  In our approach, we integrate manually defined linguistic patterns and automatically learned semi-structural templates together to extract coordinate terms.  ... 
arXiv:1507.02145v2 fatcat:2gdmd7uuw5crlmmwk4zhbmonji

ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning [article]

Hangyu Mao, Zhibo Gong, Yan Ni, Zhen Xiao
2017 arXiv   pre-print
In this paper, we propose an Actor-Coordinator-Critic Net (ACCNet) framework for solving "learning-to-communicate" problem.  ...  Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such as tabular reinforcement learning and evolutionary algorithm  ...  Acknowledgments The authors would like to thank Xiangyu Liu, Weichen Ke, Chao Ma, Quanbin Wang, Yiping Song and the anonymous reviewers for their insightful comments.  ... 
arXiv:1706.03235v3 fatcat:ejrksp7d5rchlja76n7f3icyfi

Autonomous Agents that Learn to Better Coordinate

Andrew Garland, Richard Alterman
2004 Autonomous Agents and Multi-Agent Systems  
Previous AI research on coordination has developed techniques that allow agents to act efficiently from the outset based on common built-in knowledge or to learn to act efficiently when the agents are  ...  It is a novel approach for individuals to learn procedures as a means for the group to coordinate more efficiently. Empirical results validate the utility of this approach.  ...  Agents can learn to act more efficiently even if they do not learn coordinated procedures.  ... 
doi:10.1023/b:agnt.0000018808.95119.9e fatcat:pudfz4ujt5dbfmnpisg4oeaj64

Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees [article]

Siliang Zeng, Tianyi Chen, Alfredo Garcia, Mingyi Hong
2021 arXiv   pre-print
Such kind of partially personalized policy allows agents to learn to coordinate by leveraging peers' past experience and adapt to individual tasks.  ...  Multi-agent reinforcement learning (MARL) has attracted much research attention recently.  ...  We propose and analyze a Coordinated Actor-Critic (CAC) algorithm, which allows each agent to (partially) share its policy parameters with the neighbors for learning the homogeneity / common knowledge  ... 
arXiv:2110.05597v2 fatcat:izshb7yxdbexvk4rqtfjnyldua
« Previous Showing results 1 — 15 out of 1,215,469 results