Importance Sampling for Reinforcement Learning with Multiple Objectives

Item

Title: en_US Importance Sampling for Reinforcement Learning with Multiple Objectives
Creator: en_US Shelton, Christian Robert
Date: 2004-10-01T14:00:04Z
Date Available: 2004-10-01T14:00:04Z
Date Issued: en_US 2001-08-01
Identifier: en_US AITR-2001-003; en_US CBCL-204
uri: http://hdl.handle.net/1721.1/5568
Abstract: en_US This thesis considers three complications that arise from applying reinforcement learning to a real-world application. In the process of using reinforcement learning to build an adaptive electronic market-maker, we find the sparsity of data, the partial observability of the domain, and the multiple objectives of the agent to cause serious problems for existing reinforcement learning algorithms. We employ importance sampling (likelihood ratios) to achieve good performance in partially observable Markov decision processes with few data. Our importance sampling estimator requires no knowledge about the environment and places few restrictions on the method of collecting data. It can be used efficiently with reactive controllers, finite-state controllers, or policies with function approximation. We present theoretical analyses of the estimator and incorporate it into a reinforcement learning algorithm. Additionally, this method provides a complete return surface which can be used to balance multiple objectives dynamically. We demonstrate the need for multiple goals in a variety of applications and natural solutions based on our sampling method. The thesis concludes with example results from employing our algorithm to the domain of automated electronic market-making.
Extent: en_US 108 p.; 10551422 bytes; 1268632 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-2001-003; en_US CBCL-204
Subject: en_US AI; en_US reinforcement learning; en_US RL; en_US importance sampling; en_US estimation; en_US market-making

Item sets: AI Technical Reports (1964 - 2004)