Pricing in Agent Economies Using Multi-Agent Q-Learning

By G. Tesauro, Jeffrey O. Kephart. 2002

175 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Economics and Econometrics, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Economics and Econometrics

In Management Science and Operations Research

Citations in the corpus

Stochastic Primal-Dual Q-Learning (2018, neutral): “The problem of learning a map from world observations to actions, called a policy, lies at the core of many sequential decision problems, such as robotics (Chen et al., 2017), artiﬁcial intelligence (Mnih et al., 2015), ﬁnance (Longstaﬀ and Schwartz, 2001), and economics (Tesauro and Kephart, 2002).”
Agent-Based Computational Economics: Growing Economies From the Bottom Up (2002, methodology): “Additional types of learning algorithms that have been used include action-based reinforcement learning algorithms [33, 88], Q-learning [ 92 , 104], classier systems [41], and various forms of learning algorithms that have been adapted for use in automated markets [38, 91].”
Cyclic Equilibria in Markov Games (2005, background): “Such cyclic equilibria can also be found reliably for randomly generated games and there is evidence that they appear in some naturally occurring problems (Tesauro & Kephart, 1999).”
Stochastic Primal-Dual Q-Learning Algorithm For Discounted MDPs (2019, background): “The problem of learning a map from world observations to actions, called a policy, lies at the core of many sequential decision problems, such as robotics [1], artificial intelligence [2], finance [3], and economics [4].”
Multi-agent Reinforcement Learning: An Overview (2010, methodology): “In other cases, self-interested agents interact in parallel with the market [48,98, 125].”
Adaptive treatment of anemia on hemodialysis patients: A reinforcement learning approach (2011, methodology): “The most common off-policy method is the well-known Q-learning, which has been successfully applied in many practical problems [22]–[24].”
High-level reinforcement learning in strategy games (2010, background): “Nevertheless, it has been shown to be effective [8, 12].”
Learning the IPA market with individual and social rewards (2007, unknown): “Nevertheless, Q -learning has been applied with success in several multiagent problems (for example [14], [22] and [34]) and the results obtained in this research indicate its suitability for the IPA Market.”
Artificial Intelligence, Algorithmic Pricing, and Collusion (2020, unknown): “For example, the demand function posited by Greenwald et al. (1999) and Tesauro and Kephart (2002) for the case of diﬀerentiated products is quite special.”
Cooperative Multi-Agent Learning: The State of the Art (2005, background): “Some work has applied Q-learning to extensive-form games [268] where players alternate in performing actions; but most work in the area has instead been in normal-form games where players act simultaneously.”
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning (2017, background): “This is not guaranteed theoretically and there can in fact be many problems [14], but it is often true empirically [24].”
Bias-corrected Q-learning to control max-operator bias in Q-learning (2013, methodology): “Q-learning [1] has been used in a wide range of applications, including soccer-playing robot control [2], [3], human-computer dialogue strategy [4], pricing in agent-based economy [5], mobile robot navigation [6], computer game AI development [7], agent-based production scheduling [8], and signal tr”
A Comprehensive Survey of Multiagent Reinforcement Learning (2008, unknown): “In other cases, self-interested agents interact in parallel with the market [102], [105], [106].”
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity (2017, background): “, 2007), as most research in this area seems to have focused on Q-learning for trading agents in competitive market places so far (Hsu and Soo, 2001; Tesauro and Kephart, 2002).”