Learning to Trade via Direct Reinforcement
Friday January 24, 2003
Host: Davi Geiger, email@example.com, 212-998-3235
A paradigm shift is underway in reinforcement learning (RL) research. The dominant approach to RL over the past 50 years has been based on dynamic programming, whereby RL agents learn an abstract value function. An alternative approach, Direct Reinforcement (DR), has recently been revisited, wherein DR agents learn strategies to solve problems directly. DR can enable a simpler problem representation, avoid Bellman's curse of dimensionality, and offer compelling advantages in efficiency.
We review and contrast the major approaches to RL, present Direct Reinforcement, and describe its application to asset management with transaction costs. In this very challenging and uncertain domain, DR agents seek to discover strategies that maximize profit, economic utility or risk adjusted returns. The potential powers of DR are illustrated through an asset allocator and an intradaily foreign exchange trader.
Other promising applications of DR may be found in robotics, autonomous vehicles, industrial control, telecommunications, data mining, adaptive software agents, and decision support.