Symbolic Regression Methods for Reinforcement Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Misc{DBLP:journals/corr/abs-1903-09688,

• author = "Jiri Kubalik and Jan Zegklitz and Erik Derner and Robert Babuska",
• title = "Symbolic Regression Methods for Reinforcement Learning",
• howpublished = "arXiv",
• year = "2019",
• volume = "abs/1903.09688",
• month = "22 " # mar,
• keywords = "genetic algorithms, genetic programming, reinforcement learning, value iteration, policy iteration, symbolic regression, nonlinear optimal control",
• URL = "http://arxiv.org/abs/1903.09688",
• size = "12 pages",
• abstract = "Reinforcement learning algorithms can be used to optimally solve dynamic decision-making and control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis function expansions, have two main drawbacks: they are black-box models offering no insight in the mappings learned, and they require significant trial and error tuning of their meta-parameters. In this paper, we propose a new approach to constructing smooth value functions by means of symbolic regression. We introduce three off-line methods for finding value functions based on a state transition model: symbolic value iteration, symbolic policy iteration, and a direct solution of the Bellman equation. The methods are illustrated on four nonlinear control problems: velocity control under friction, one-link and two-link pendulum swing-up,",

}

Genetic Programming entries for Jiri Kubalik Jan Zegklitz Erik Derner Robert Babuska

Citations