Market Performance of Adaptive Trading Agents in Synchronous Double Auctions

We are concerned with the issues on designing adaptive trading agents to learn bidding strategies in electronic market places. The synchronous double auction is used as a simulation testbed. We implemented agents with neural-network-based reinforcement learning called Q-learning agents (QLA) to learn bidding strategies in the double auctions. In order to compare the performances of QLAs in the electronic market places, we also implemented many kinds of non-adaptive trading agents such as simple random bidding agents (SRBA), gradient-based greedy agent (GBGA), and truth telling agent (TTA). Instead of learning to model other trading agents that is computational intractable, we designed learning agents to model the market environment as a whole instead. Our experimental results showed that in terms of global market efficiency, QLAs could outperform TTAs and GBGAs but could not outperform SRBAs in the market of homogeneous type of agents. In terms of individual performance, QLAs could outperform all three non-adaptive trading agents when the opponents they are dealing with in the market place are a purely homogeneous type of non-adaptive trading agents. However, QLAs could only outperform TTAs and GBGAs and could not outperform SRBAs in the market of heterogeneous types of agents.

[1]  Edmund H. Durfee,et al.  An adaptive agent bidding strategy based on stochastic modeling , 1999, AGENTS '99.

[2]  Pere Garcia-Calvés,et al.  Designing bidding strategies for trading agents in electronic auctions , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).

[3]  William Vickrey,et al.  Counterspeculation, Auctions, And Competitive Sealed Tenders , 1961 .

[4]  R. L. Keeney,et al.  Decisions with Multiple Objectives: Preferences and Value Trade-Offs , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  A. Sadrieh.  The Alternating Double Auction Market: A Game Theoretic and Experimental Investigation , 1998 .

[6]  Michael P. Wellman,et al.  A Parametrization of the Auction Design Space , 2001, Games Econ. Behav..

[7]  Michael P. Wellman,et al.  Online learning about other agents in a dynamic multiagent system , 1998, AGENTS '98.

[8]  Chris Preist,et al.  Commodity trading using an agent-based iterated double auction , 1999, AGENTS '99.

[9]  Steven R. Williams,et al.  The Double Auction Market: Institutions , 1991 .

[10]  J. Kagel,et al.  Handbook of Experimental Economics , 1997 .

[11]  Dhananjay K. Gode,et al.  Allocative Efficiency of Markets with Zero-Intelligence Traders: Market as a Partial Substitute for Individual Rationality , 1993, Journal of Political Economy.

[12]  Sandip Sen,et al.  A buyer's agent , 2000, AGENTS '00.

[13]  Daniel M. Reeves,et al.  Agent Service for Online Auctions , 1999 .

[14]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[15]  D. Cliff,et al.  Zero is Not Enough: On The Lower Limit of Agent Intelligence For Continuous Double Auction Markets† , 1997 .

[16]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[17]  Abdolkarim Sadrieh,et al.  The Alternating Double Auction Market , 1998 .

[18]  Michael P. Wellman,et al.  Flexible double auctions for electronic commerce: theory and implementation , 1998, Decis. Support Syst..

[19]  R. McAfee,et al.  Auctions and Bidding , 1986 .

[20]  E. Durfee,et al.  The Impact of Nested Agent Models in an Information Economy , 1996 .

[21]  Ralph L. Keeney,et al.  Decisions with multiple objectives: preferences and value tradeoffs , 1976 .

[22]  Robert H. Wilson.  Incentive Efficiency of Double Auctions , 1985 .