Optimal Control via Reinforcement Learning with Symbolic Policy Approximation
Created by W.Langdon from
gp-bibliography.bib Revision:1.8178
- @Article{KUBALIK:2017:IFAC-PapersOnLine,
-
author = "Jiri Kubalik and Eduard Alibekov and Robert Babuska",
-
title = "Optimal Control via Reinforcement Learning with
Symbolic Policy Approximation",
-
journal = "IFAC-PapersOnLine",
-
volume = "50",
-
number = "1",
-
pages = "4162--4167",
-
year = "2017",
-
note = "20th IFAC World Congress",
-
keywords = "genetic algorithms, genetic programming, reinforcement
learning, value iteration, symbolic regression,
nonlinear model-based control, optimal control",
-
ISSN = "2405-8963",
-
DOI = "doi:10.1016/j.ifacol.2017.08.805",
-
URL = "http://www.sciencedirect.com/science/article/pii/S2405896317312594",
-
abstract = "Model-based reinforcement learning (RL) algorithms can
be used to derive optimal control laws for nonlinear
dynamic systems. With continuous-valued state and input
variables, RL algorithms have to rely on function
approximators to represent the value function and
policy mappings. This paper addresses the problem of
finding a smooth policy based on the value function
represented by means of a basis-function approximator.
We first show that policies derived directly from the
value function or represented explicitly by the same
type of approximator lead to inferior control
performance, manifested by non-smooth control signals
and steady-state errors. We then propose a novel method
to construct a smooth policy represented by an analytic
equation, obtained by means of symbolic regression. The
proposed method is illustrated on a reference-tracking
problem of a 1-DOF robot arm operating under the
influence of gravity. The results show that the
analytic control law performs at least equally well as
the original numerically approximated policy, while it
leads to much smoother control signals. In addition,
the analytic function is readable (as opposed to
black-box approximators) and can be used in further
analysis and synthesis of the closed loop",
- }
Genetic Programming entries for
Jiri Kubalik
Eduard Alibekov
Robert Babuska
Citations