Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom Navigation Tasks

Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom... Modularity represents a recurring theme in the attempt to scale evolution to the design of complex systems. However, modularity rarely forms the central theme of an artificial approach to evolution. In this work, we report on progress with the recently proposed Tangled Program Graph (TPG) framework in which programs are modules. The combination of the TPG representation and its variation operators enable both teams of programs and graphs of teams of programs to appear in an emergent process. The original development of TPG was limited to tasks with, for the most part, complete information. This work details two recent approaches for scaling TPG to tasks that are dominated by partially observable sources of information using different formulations of indexed memory. One formulation emphasizes the incremental construction of memory, again as an emergent process, resulting in a distributed view of state. The second formulation assumes a single global instance of memory and develops it as a communication medium, thus a single global view of state. The resulting empirical evaluation demonstrates that TPG equipped with memory is able to solve multi-task recursive time-series forecasting problems and visual navigation tasks expressed in two levels of a commercial first-person shooter environment. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Evolutionary Learning and Optimization Association for Computing Machinery

Emergent Tangled Program Graphs in Partially Observable Recursive Forecasting and ViZDoom Navigation Tasks

Loading next page...
 
/lp/association-for-computing-machinery/emergent-tangled-program-graphs-in-partially-observable-recursive-KDRLgzGOap
Publisher
Association for Computing Machinery
Copyright
Copyright © 2001 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISSN
2688-299X
eISSN
2688-3007
DOI
10.1145/3468857
Publisher site
See Article on Publisher Site

Abstract

Modularity represents a recurring theme in the attempt to scale evolution to the design of complex systems. However, modularity rarely forms the central theme of an artificial approach to evolution. In this work, we report on progress with the recently proposed Tangled Program Graph (TPG) framework in which programs are modules. The combination of the TPG representation and its variation operators enable both teams of programs and graphs of teams of programs to appear in an emergent process. The original development of TPG was limited to tasks with, for the most part, complete information. This work details two recent approaches for scaling TPG to tasks that are dominated by partially observable sources of information using different formulations of indexed memory. One formulation emphasizes the incremental construction of memory, again as an emergent process, resulting in a distributed view of state. The second formulation assumes a single global instance of memory and develops it as a communication medium, thus a single global view of state. The resulting empirical evaluation demonstrates that TPG equipped with memory is able to solve multi-task recursive time-series forecasting problems and visual navigation tasks expressed in two levels of a commercial first-person shooter environment.

Journal

ACM Transactions on Evolutionary Learning and OptimizationAssociation for Computing Machinery

Published: Aug 18, 2021

Keywords: Coevolution

References