Learning World Models in Environments with Manifest Causal Structure

Item

Title: en_US Learning World Models in Environments with Manifest Causal Structure
Creator: en_US Bergman, Ruth
Date: 2004-10-20T14:45:25Z
Date Available: 2004-10-20T14:45:25Z
Date Issued: en_US 1995-05-05
Identifier: en_US AITR-1513
uri: http://hdl.handle.net/1721.1/6777
Abstract: en_US This thesis examines the problem of an autonomous agent learning a causal world model of its environment. Previous approaches to learning causal world models have concentrated on environments that are too "easy" (deterministic finite state machines) or too "hard" (containing much hidden state). We describe a new domain --- environments with manifest causal structure --- for learning. In such environments the agent has an abundance of perceptions of its environment. Specifically, it perceives almost all the relevant information it needs to understand the environment. Many environments of interest have manifest causal structure and we show that an agent can learn the manifest aspects of these environments quickly using straightforward learning techniques. We present a new algorithm to learn a rule-based causal world model from observations in the environment. The learning algorithm includes (1) a low level rule-learning algorithm that converges on a good set of specific rules, (2) a concept learning algorithm that learns concepts by finding completely correlated perceptions, and (3) an algorithm that learns general rules. In addition this thesis examines the problem of finding a good expert from a sequence of experts. Each expert has an "error rate"; we wish to find an expert with a low error rate. However, each expert's error rate and the distribution of error rates are unknown. A new expert-finding algorithm is presented and an upper bound on the expected error rate of the expert is derived.
Extent: en_US 142 p.; 12411678 bytes; 1775267 bytes
Format: application/postscript; application/pdf
Language: en_US
Relation: en_US AITR-1513
Subject: en_US machine learning; en_US intelligent agents

Item sets: AI Technical Reports (1964 - 2004)