Using Landscape Theory to Measure Learning Difficulty for Adaptive Agents Export

@incollection{brooks03a, abstract = {We compare the usefullness of three different metrics for estimating ruggedness on learning problems in an information economy domain.We empirically evaluate the ability of each metric to predict ruggedness and use these metrics to explain past results showing that problems that yield equal reward when completely learned yield different profits to an adaptive learning agent.}, author = {Brooks, Christopher H. and Durfee, Edmund H.}, booktitle = {Adaptive Agents and Multi-Agent Systems}, citeulike-article-id = {1585751}, citeulike-linkout-0 = {http://jmvidal.cse.sc.edu/library/brooks03a.pdf}, keywords = {bibtex-import, complexity, learning, multiagent}, posted-at = {2007-08-23 14:42:25}, priority = {2}, publisher = {Lecture Notes in Artificial Intelligence, Springer-Verlag}, title = {Using Landscape Theory to Measure Learning Difficulty for Adaptive Agents}, url = {http://jmvidal.cse.sc.edu/library/brooks03a.pdf}, year = {2003} }

TY - CHAP ID - brooks03a L3 - citeulike-article-id:1585751 N2 - We compare the usefullness of three different metrics for estimating ruggedness on learning problems in an information economy domain.We empirically evaluate the ability of each metric to predict ruggedness and use these metrics to explain past results showing that problems that yield equal reward when completely learned yield different profits to an adaptive learning agent. TI - Using Landscape Theory to Measure Learning Difficulty for Adaptive Agents PB - Lecture Notes in Artificial Intelligence, Springer-Verlag T2 - Adaptive Agents and Multi-Agent Systems KW - bibtex-import KW - complexity KW - learning KW - multiagent AU - Brooks, Christopher AU - Durfee, Edmund PY - 2003/// UR - http://jmvidal.cse.sc.edu/library/brooks03a.pdf ER -