@TechReport{	  it:2022-006,
  author	= {Ruoqi Zhang and Per Mattsson and Torbj{\"o}rn Wigren},
  title		= {A Robust Multi-Goal Exploration Aided Tracking Policy},
  institution	= {Department of Information Technology, Uppsala University},
  department	= {Division of Scientific Computing},
  year		= {2022},
  number	= {2022-006},
  month		= jun,
  abstract	= {Set-point control aims at finding a policy that can track
		  a set point that varies over time. Such control objectives
		  are central in industry, yet multi-goal Reinforcement
		  Learning methods are typically evaluated on other
		  environments. The paper therefore proposes the use of a
		  combination of feedback based amplitude aided exploration,
		  simulated ensemble model training, together with policy
		  optimization also over integrated errors, to arrive at a
		  trained multi-goal policy that can be directly deployed to
		  real-world nonlinear set-point control systems. The claim
		  is supported by experiments with a real-world nonlinear
		  cascaded tank process and a simulated strongly non-linear
		  pH-control system.}
}