Accelerating Tangled Program Graph Evolution under Visual Reinforcement Learning Tasks with Mutation and Multi-actions

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Bayer:2021:GPTP,

• author = "Caleidgh Bayer and Ryan Amaral and Robert Smith and Alexandru Ianta and Malcolm Heywood",
• title = "Accelerating Tangled Program Graph Evolution under Visual Reinforcement Learning Tasks with Mutation and Multi-actions",
• booktitle = "Genetic Programming Theory and Practice XVIII",
• year = "2021",
• editor = "Wolfgang Banzhaf and Leonardo Trujillo and Stephan Winkler and Bill Worzel",
• series = "Genetic and Evolutionary Computation",
• pages = "1--19",
• address = "East Lansing, USA",
• month = "19-21 " # may,
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming",
• isbn13 = "978-981-16-8112-7",
• DOI = "doi:10.1007/978-981-16-8113-4_1",
• abstract = "Tangled Program Graphs (TPG) represents a genetic programming framework in which emergent modularity incrementally composes programs into teams of programs into graphs of teams of programs. To date, the framework has been demonstrated on reinforcement learning tasks with stochastic partially observable state spaces or time series prediction. However, evolving solutions to reinforcement tasks often requires agents to demonstrate/ juggle multiple properties simultaneously. Hence, we are interesting in maintaining a population of diverse agents. Specifically, agent performance on a reinforcement learning task controls how much of the task they are exposed to. Premature convergence might therefore preclude solving aspects of a task that the agent only later encounters. Moreover, pointless complexity may also result in which graphs largely consist of hitchhikers. In this research we benchmark the use of rampant mutation (multiple mutations applied simultaneously for offspring creation) and action programs (multiple actions per state). Several parameterizations are also introduced that potentially penalize the introduction of hitchhikers. Benchmarking over five VizDoom tasks demonstrates that rampant mutation reduces the likelihood of encountering pathologically bad offspring while action programs appears to improve performance in four out of five tasks. Finally, use of TPG parameterizations that actively limit the complexity of solutions appears to result in very efficient low dimensional solutions that generalize best across all combinations of 3, 4 and 5 VizDoom tasks.",
• notes = "Part of \cite{Banzhaf:2021:GPTP} published after the workshop in 2022",

}

Genetic Programming entries for Caleidgh Bayer Ryan Amaral Robert J Smith Alexandru Ianta Malcolm Heywood

Citations