3,066 Hits in 4.2 sec

Using Multi-Agent Reinforcement Learning in Auction Simulations [article]

Medet Kanmaz, Elif Surer
2020 arXiv   pre-print
The results show that using a multi-agent reinforcement learning strategy improves the outcomes of the auction simulations.  ...  In this study, the strategic (rational) agents created by reinforcement learning algorithms are supposed to be bidder agents in various types of auction mechanisms such as British Auction, Sealed Bid Auction  ...  In this paper, multi-agent reinforcement learning agents in different auction setups were created.  ... 
arXiv:2004.02764v1 fatcat:haxdupddxbg4dazwrv5qbq4xxe

Learning Task Performance in Market-Based Task Allocation [chapter]

Charles E. Pippin, Henrik Christensen
2013 Advances in Intelligent Systems and Computing  
Experimental results demonstrate that agents that model team member performance using this approach can more efficiently distribute tasks in multi-agent auctions.  ...  A policy gradient reinforcement learning algorithm is used to learn a cost factor that can be applied individually to auction bids.  ...  In Section II, we present the background and related work for learning in multi-agent auctions. In Section III, we discuss the use of the reinforcement learning algorithm within an auction framework.  ... 
doi:10.1007/978-3-642-33932-5_57 fatcat:rxvt75ge6bagranghcysnbllki

Designing Multi-unit Multiple Bid Auctions: An Agent-based Computational Model of Uniform, Discriminatory and Generalised Vickrey Auctions

2007 The Economic Record  
Designing multi-unit multiple bid auctions: an agent-based computational model of uniform, discriminatory and generalised Vickrey Auctions. Economic Record, 83 (S1), S57-S72.  ...  An agent-based model was then formulated to simulate bidding among a population of agents that use a reinforcement learning algorithm to update their bids based on individual experience.  ...  In the third section, we develop an agent-based model (ABM) of boundedly rational bidders revising their bid choices using Erev and Roth's (1998) reinforcement learning algorithm.  ... 
doi:10.1111/j.1475-4932.2007.00410.x fatcat:hjnmvgaqorb5hhn5ci5mlifa6a

Market-Based Dynamic Task Allocation Using Heuristically Accelerated Reinforcement Learning [chapter]

José Angelo Gurzoni, Flavio Tonidandel, Reinaldo A. C. Bianchi
2011 Lecture Notes in Computer Science  
, and use Heuristically Accelerated Reinforcement Learning to evaluate their aptitude to perform these roles, given the situation of the team, in real-time.  ...  This paper presents a Multi-Robot Task Allocation (MRTA) system, implemented on a RoboCup Small Size League team, where robots participate of auctions for the available roles, such as attacker or defender  ...  The authors also believe that more research into the topic of transfer learning for RL domains [19] could considerably improve the capabilities to apply what was learned in simulation to real robots.  ... 
doi:10.1007/978-3-642-24769-9_27 fatcat:joi2w7jnvvf3tbqqtyvbz3zzp4

Comparison of Different Auction Pricing Rules in the Electricity Market

Ly Fie Sugianto, Kevin Zhigang Liao
2014 Modern Applied Science  
The Simulated-Annealing Q-learning algorithm has been adopted as the learning mechanism for the agents so they can maximize their profit using strategic bidding.  ...  Using agent-based modeling approach, generators have been modelled as agents submitting price-quantity bids to the market.  ...  market to be designed carefully to ensure that (1) it is attractive for new players, which hopefully will bring about newer and cleaner power generation technology into use, and (2) it results in a competitive  ... 
doi:10.5539/mas.v8n1p147 fatcat:noquaae4fnhhzanktatusyhedy

Deep Reinforcement Learning for Sponsored Search Real-time Bidding [article]

Jun Zhao, Guang Qiu, Ziyu Guan, Wei Zhao, Xiaofei He
2018 arXiv   pre-print
We also extend the method to handle the multi-agent problem. We deployed the SS-RTB system in the e-commerce search auction platform of Alibaba.  ...  We propose a reinforcement learning (RL) solution for handling the complex dynamic environment.  ...  No previous work has explored using cooperative rewards to address the multi-agent problem in such scenarios.  ... 
arXiv:1803.00259v1 fatcat:kqjd46oojfdh5p2kin42w7muua

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

Kristof Van Moffaert, Tim Brys, Arjun Chandra, Lukas Esterle, Peter R. Lewis, Ann Nowe
2014 2014 International Joint Conference on Neural Networks (IJCNN)  
Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup.  ...  multi-agent learning domain has not yet been thoroughly investigated.  ...  Multi-objective reinforcement learning (MORL) is an extension to reinforcement learning (RL) where the environment provides the agent with multiple feedback signals.  ... 
doi:10.1109/ijcnn.2014.6889637 dblp:conf/ijcnn/MoffaertBCELN14 fatcat:cdg6m4gzo5amxeswcg6egcahue

Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning

Justin Fu, Andrea Tacchetti, Julien Perolat, Yoram Bachrach
2021 The Journal of Artificial Intelligence Research  
We show how to efficiently and scalably extend inverse reinforcement learning to multi-agent settings, by reducing the multi-agent problem to N single-agent problems while still satisfying rationality  ...  A core question in multi-agent systems is understanding the motivations for an agent's actions based on their behavior.  ...  multi-agent inverse reinforcement learning and inverse game theory.  ... 
doi:10.1613/jair.1.12594 fatcat:evyejc6srnafbb3a6zvsrktf2m

Comparing Policy Gradient and Value Function Based Reinforcement Learning Methods in Simulated Electrical Power Trade

Richard Lincoln, Stuart Galloway, Bruce Stephen, Graeme Burt
2012 IEEE Transactions on Power Systems  
Graeme (2012) Comparing policy gradient and value function based reinforcement learning methods in simulated electrical power trade.  ...  Abstract-In electrical power engineering, reinforcement learning algorithms can be used to model the strategies of electricity market participants.  ...  Similarly, the authors are very grateful to the researchers from Dalle Molle Institute for Artificial Intelligence (IDSIA) and the Technical University of Munich involved in developing the reinforcement  ... 
doi:10.1109/tpwrs.2011.2166091 fatcat:wgiev5eo3zfh3aypbx4l675osu

Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising [article]

Junqi Jin, Chengru Song, Han Li, Kun Gai, Jun Wang, Weinan Zhang
2018 arXiv   pre-print
In this paper, we formulate bidding optimization with multi-agent reinforcement learning.  ...  A practical Distributed Coordinated Multi-Agent Bidding (DCMAB) has been proposed and implemented to balance the tradeoff between the competition and cooperation among advertisers.  ...  In our work, we adopt multi-agent reinforcement learning to achieve such a goal. Multi-agent Reinforcement Learning.  ... 
arXiv:1802.09756v1 fatcat:f4ikpoio3neyxfziactsvjwdxu

Market-Driven Multi-Agent Collaboration in Robot Soccer Domain [chapter]

Hatice Kose, Kemal Kaplan, Cetin Mericli, Utku Tatlidede, Levent Aki
2005 Cutting Edge Robotics  
Although Teambots is not used in any international robot soccer competition, it is a well-known multi-purpose simulator.  ...  multi-agent teams in key application areas.  ...  The chapter IV is devoted to research on adaptive and learning systems in mobile robots area. The chapter V speaks about different application areas of multi-robot systems.  ... 
doi:10.5772/4661 fatcat:bhi7duaoerfqhaspd27arc6yta

A Systematic Approach for Including Machine Learning in Multi-agent Systems [chapter]

José A. R. P. Sardinha, Alessandro Garcia, Carlos J. P. Lucena, Ruy L. Milidiú
2005 Lecture Notes in Computer Science  
Large scale multi-agent systems (MASs) in unpredictable environments must use machine learning techniques to perform their goals and improve the performance of the system.  ...  This paper presents a systematic approach to introduce machine learning in the design and implementation phases of a software agent.  ...  Introduction Multi-Agent Systems (MASs) [1] [2] is a new technology that has been recently used in many simulators and intelligent systems to help humans perform several timeconsuming tasks.  ... 
doi:10.1007/11426714_14 fatcat:h5el2dxynzcsrj237gpmnasrly

On the Importance of Opponent Modeling in Auction Markets [article]

Mahmoud Mahfouz, Angelos Filos, Cyrine Chtourou, Joshua Lockhart, Samuel Assefa, Manuela Veloso, Danilo Mandic, Tucker Balch
2019 arXiv   pre-print
To this end, we demonstrate the efficacy of applying opponent-modeling in a number of simulated market settings.  ...  While our simulations are simplified representations of actual market dynamics, they provide an idealized "playground" in which our techniques can be demonstrated and tested.  ...  in any way for evaluating the merits of participating in any transaction.  ... 
arXiv:1911.12816v1 fatcat:7io7sz4xnrex7pzzrk7lefcipy

What Format for Multi-Unit Multiple-Bid Auctions?

Atakelty Hailu, Sophie Thoyer
2010 Computational Economics  
However, there is great uncertainty about the best auction formats when multi-unit auctions are used.  ...  This paper uses computational experiments where bidders learn over nonlinear bidding strategies to compare outcomes for alternative pricing format for multi-unit multiple-bid auctions.  ...  In our simulations, we find a much greater variability in auction outcomes across replications when reinforcement learning used.  ... 
doi:10.1007/s10614-010-9199-x fatcat:aeikd6o3ijav7pvk6kibei5zba

Comparison of Market-based and DQN methods for Multi-Robot processing Task Allocation (MRpTA)

Paul Gautier, Johann Laurent, Jean-Philippe Diguet
2020 2020 Fourth IEEE International Conference on Robotic Computing (IRC)  
Market-based methods are a natural candidate to deal processing tasks over a MRS but recent and numerous developments in reinforcement learning and especially Deep Q-Networks (DQN) provide new opportunities  ...  Our study shows the relevancy of learning-based methods and also highlight research challenges to solve the processing load-balancing problem in MRS.  ...  To overcome this problem, we propose another approach based on reinforcement learning. B. Reinforcement learning One of the main goals of our RL approach is to remove the auction system.  ... 
doi:10.1109/irc.2020.00060 fatcat:n5cv2jqcnnerrdkj673sgpe3ue
« Previous Showing results 1 — 15 out of 3,066 results