Adaptive Trading Agent Strategies Using Market
Experience
Publication No.
David Merrill Pardoe, Ph.D.
The University of Texas at Austin, 2011
Supervisor: Peter Stone
Along with the growth of electronic commerce has come an interest in devel-
oping autonomous trading agents. Often, such agents must interact directly with
other market participants, and so the behavior of these par ticipants must be taken
into account when designing agent strategies. One common approach is to build a
model of the market, but this approach requires the use o f historical market dat a,
which may not always be available. This dissertation addresses such a case: t hat of
an agent entering a new market in which it has no previous experience. While the
agent could adapt by learning about the behavior of other market participants, it
would need to do so in an online fashion. The agent would not necessarily have to
learn from scratch, however. If the agent ha d previous experience in similar mar-
kets, it could use this experience to tailor its learning approach to its particular
situation.
This dissertation explores methods that a trading agent could use to take
advantage of previous market experience when adapting t o a new market. Two dis-
tinct learning settings are considered. In the first, an agent acting as an auctioneer
iv
