2,986 Hits in 8.0 sec

Multi-agent Q-learning and Regression Trees for Automated Pricing Decisions [chapter]

Manu Sridharan, Gerald Tesauro
2002 Multiagent Systems, Artificial Societies, and Simulated Organizations  
We study the use of single-agent and multiagent Q-learning to learn seller pricing strategies in three di erent two-seller models of agent economies, using a simple regression tree approximation scheme  ...  Also, with regression trees, Q-learning appears much more feasible as a practical approach to learning strategies in large multi-agent economies.  ...  Single and Multi-agent Q-learning Learning algorithm The standard procedure for Q-learning is as follows.  ... 
doi:10.1007/978-1-4615-1107-6_11 fatcat:xueirzq2lrhh5dou4zcuhsb2su

Multi-agent Q-learning and regression trees for automated pricing decisions

M. Sridharan, G. Tesauro
Proceedings Fourth International Conference on MultiAgent Systems  
We study the use of single-agent and multiagent Q-learning to learn seller pricing strategies in three di erent two-seller models of agent economies, using a simple regression tree approximation scheme  ...  Also, with regression trees, Q-learning appears much more feasible as a practical approach to learning strategies in large multi-agent economies.  ...  Single and Multi-agent Q-learning Learning algorithm The standard procedure for Q-learning is as follows.  ... 
doi:10.1109/icmas.2000.858518 dblp:conf/icmas/SridharanT00 fatcat:xiixmgcribcobk5ncw4zevtc4a

Stock Market Trading Based on Market Sentiments and Reinforcement Learning

K. M. Ameen Suhail, Syam Sankar, Ashok S. Kumar, Tsafack Nestor, Naglaa F. Soliman, Abeer D. Algarni, Walid El-Shafai, Fathi E. Abd El-Samie
2022 Computers Materials & Continua  
In this paper, we report a system that uses a Reinforcement Learning (RL) network and market sentiments to make decisions about stock market trading.  ...  It is a collection of buyers' and sellers' stocks. In this digital era, analysis and prediction in the stock market have gained an essential role in shaping today's economy.  ...  [16] explained a model based on supervised machine learning, logistic regression, boosted decision tree and SVM for predicting daily stock prices and monthly stock prices.  ... 
doi:10.32604/cmc.2022.017069 fatcat:huainle2kjhfnjvdbpiatyjfga

Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review

Ioannis Antonopoulos, Valentin Robu, Benoit Couraud, Desen Kirli, Sonam Norbu, Aristides Kiprakis, David Flynn, Sergio Elizondo-Gonzalez, Steve Wattam
2020 Renewable & Sustainable Energy Reviews  
The work was also supported by the UK Engineering and Physical Sciences Council  ...  Acknowledgements The authors would like to acknowledge the support of the Energy Technology Partnership Scotland (ETP) through their Industry Doctorates scheme and our industrial sponsor Upside Energy.  ...  [54] use Gradient boosting decision tree (GBDT) to build an additive regression model, with the use of regression trees as the weak learner.  ... 
doi:10.1016/j.rser.2020.109899 fatcat:wgpj4awq35dfzdq7ugumtrvo7q

Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach [article]

Mao Guan, Xiao-Yang Liu
2021 arXiv   pre-print
Secondly, for DRL agents, we use integrated gradients to define the feature weights, which are the coefficients between reward and features under a linear regression model.  ...  In particular, we quantify the prediction power by calculating the linear correlations between the feature weights of a DRL agent and the reference feature weights, and similarly for machine learning methods  ...  Policy Optimization (PPO), Decision Tree (DT), Linear Regression (LR), Support Vector Machine (SVM) and Random Forest (RF).  ... 
arXiv:2111.03995v2 fatcat:t4hcw2hxqzedfb5luyx5u6gble

Auction optimization using regression trees and linear models as integer programs

Sicco Verwer, Yingqian Zhang, Qing Chuan Ye
2017 Artificial Intelligence  
To this end, we provide efficient encodings of regression trees and linear regression models as ILP constraints. This new way of using learned models for optimization is promising.  ...  We learn regression models from historical auctions, which are subsequently used to predict the expected value of orderings for new auctions.  ...  Gabel and Riedmiller [1] model production scheduling problem as multi-agent reinforcement learning where each agent makes its dispatching decisions using a reinforcement learning algorithm based on a  ... 
doi:10.1016/j.artint.2015.05.004 fatcat:kh67ekf245an3jva7gno7ovmoe

Improving Agent Bidding in Power Stock Markets through a Data Mining Enhanced Agent Platform [chapter]

Anthony C. Chrysopoulos, Andreas L. Symeonidis, Pericles A. Mitkas
2009 Lecture Notes in Computer Science  
Within the context of this paper we present Cassandra, a multi-agent platform that exploits data mining, in order to extract efficient models for predicting Power Settlement prices and Power Load values  ...  Decisions become even more difficult to make in case one takes the vast volumes of historical data available into account: goods' prices, market fluctuations, bidding habits and buying opportunities.  ...  SEPIA employs two different options for agent learning: a variation of the Q-Learning Algorithm [7] , which corresponds each noticeable state to a suitable action, and an LCS (Learning Classifier System  ... 
doi:10.1007/978-3-642-03603-3_9 fatcat:tqi7hzyqfjecre5ka3mhzzc3fu

Learning FX trading strategies with FQI and persistent actions

Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli
2021 Proceedings of the Second ACM International Conference on AI in Finance  
In this paper, we formulate multi-currency trading as a Markov Decision Process and we train an agent via Fitted-Q Iteration, a Reinforcement Learning value-based algorithm.  ...  objectives for autonomous agents.  ...  ACKNOWLEDGMENTS The research was conducted under a cooperative agreement between Intesa Sanpaolo IMI Corporate & Investment Banking Division and Politecnico di Milano.  ... 
doi:10.1145/3490354.3494403 fatcat:so3fihxvvbaxbeavswaeef6bvq

Page 6437 of Mathematical Reviews Vol. , Issue 2004h [page]

2004 Mathematical Reviews  
Stearns, Polynomial-time mechanisms for collective decision making (197-216); Manu Srid- haran and Gerald Tesauro, Multi-agent Q-learning and regression trees for automated pricing decisions (217-234);  ...  Kephart, Pricing in agent economies using multi-agent Q-learning (293-313); Russell Vane and Paul Lehner, Using hypergames to increase planned payoff and reduce risk (315-336); Julita Vas- sileva and Chhaya  ... 

ANEGMA: an automated negotiation model for e-markets

Pallavi Bagga, Nicola Paoletti, Bedour Alrayes, Kostas Stathis
2021 Autonomous Agents and Multi-Agent Systems  
As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed.  ...  AbstractWe present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets.  ...  These include: [61] which combines evolutionary algorithms and reinforcement learning, [49] which combines regression trees with single-agent and multi-agent Q-learning, and [50] which proposes a  ... 
doi:10.1007/s10458-021-09513-x fatcat:x7nsbxywxbed5bznj3xq4ykpdy

Modelling the transition to a low-carbon energy supply [article]

Alexander Kell
2021 arXiv   pre-print
machine learning and artificial intelligence methods.  ...  Therefore, a low-carbon transition is required, however, the decisions various stakeholders should make over the coming decades to reduce these carbon emissions are not obvious.  ...  Random Forests are an ensemble-based learning method for classification and regression, and are made up of many decision trees.  ... 
arXiv:2111.00987v1 fatcat:cltjuirij5fvfhxeoonaxqrs4m

Classification Model for Prediction of Heart Disease using Correlation Coefficient Technique

Sireesha Moturi
2020 International Journal of Advanced Trends in Computer Science and Engineering  
So, there is a necessity to develop a decision making system which will helps practitioners to predict heart diseases in an easier way and will offer automated predictions about the condition of the patient's  ...  The Machine Learning algorithms have determined to be most accurate & reliable and hence used in this paper.  ...  In regression problem it considers mean of K labels and in classification problem it considers mode of K labels. Decision Tree: It is one of the famous methods for supervised learning problems.  ... 
doi:10.30534/ijatcse/2020/185922020 fatcat:25b5rckt5nem5lz44fncwyk5lu

FinBrain: When Finance Meets AI 2.0 [article]

Xiaolin Zheng, Mengying Zhu, Qibing Li, Chaochao Chen, Yanchao Tan
2018 arXiv   pre-print
and robust decision making, and multi-agent game and mechanism design.  ...  In our current dynamic capital market, financial intelligence demonstrates a fast and accurate machine learning capability to handle complex data and has gradually acquired the potential to become a "financial  ...  Learning to play a multi-agent game is crucial in robust credit systems, supply chain management, dynamic asset pricing, and trading mechanism design.  ... 
arXiv:1808.08497v1 fatcat:rg2xjtsu4bhelgzwo3ifggai4y

Predictive Market Making via Machine Learning

Abbas Haider, Hui Wang, Bryan Scotney, Glenn Hawe
2022 SN Operations Research Forum  
In this paper, we introduce the concept of predictive market marking (PMM) and present our method for PMM, which comprises a RL-based MM agent and a deep neural network (DNN)-based price predictor.  ...  In the latest work on RL-based MM, the reward is a function of equity returns, calculated based on its current price, and the inventory of MM agent.  ...  We use a simple regression tree-based model for price prediction and conducted out-of-sample backtesting (see Table 3 ).  ... 
doi:10.1007/s43069-022-00124-0 fatcat:geagrdxaebeafgpiaztfajaec4

Artificial intelligence in computer networks

Tanya Abdulsattar Jaber
2022 Periodicals of Engineering and Natural Sciences (PEN)  
procedures that are represented by specific algorithms along with (learning, reasoning, as well as selfcorrection).  ...  Using the AI-based approaches has been researched at first in the applications that are associated with the optic transmissions, beginning by characterizing and operating the additives of the network for  ...  The methods comprise the logistic regression, linear regression, ANNs, decision trees, SVMs and nearest neighbor models.  ... 
doi:10.21533/pen.v10i1.2616 fatcat:k7qoar55wvh5jesjza22tar4uq
« Previous Showing results 1 — 15 out of 2,986 results