Difference between revisions of "SC²S Colloquium - June 4, 2013"

From Sccswiki
Jump to navigation Jump to search
(Created page with "{| class="wikitable" |- | '''Date:''' || June 6, 2013 |- | '''Room:''' || 02.07.023 |- | '''Time:''' || 3 pm, s.t. |- |} == Torsten Koller: Employing Policy Search Technique...")
 
Line 25: Line 25:
 
and discontinuances, throttle valve control is an especially challenging
 
and discontinuances, throttle valve control is an especially challenging
 
control task. In this thesis the Policy Search algorithm Pilco is
 
control task. In this thesis the Policy Search algorithm Pilco is
modi�ed to learn throttle valve control from data. In contrast to modelfree
+
modied to learn throttle valve control from data. In contrast to modelfree
 
PID control or model-based controllers no sophisticated knowledge of
 
PID control or model-based controllers no sophisticated knowledge of
 
the system nor tedious manual parameter tuning is required. To adress
 
the system nor tedious manual parameter tuning is required. To adress
task-speci�c challenges and requirements such as high frequency control,
+
task-specic challenges and requirements such as high frequency control,
 
no-overshoot and the control of arbitrary desired trajectories, several  
 
no-overshoot and the control of arbitrary desired trajectories, several  
 
theoretical
 
theoretical

Revision as of 20:10, 22 May 2013

Date: June 6, 2013
Room: 02.07.023
Time: 3 pm, s.t.


Torsten Koller: Employing Policy Search Techniques for Learning Throttle Valve Control

The aim of this thesis is to demonstrate the viability of reinforcement learning (RL) in challenging real-world problems such as throttle valve control. The throttle valve is a mechanical device which regulates the flow of a fluid or gas. Numerous applications of throttle valves can be found in industrial processes and systems such as refrigerators, semiconductor manufacturing and waterworks. One of the most important applications however is the gasoline throttle valve system regulating the amount of air entering the combustion engine. Due to high dynamics of the system including nonlinearities and discontinuances, throttle valve control is an especially challenging control task. In this thesis the Policy Search algorithm Pilco is modied to learn throttle valve control from data. In contrast to modelfree PID control or model-based controllers no sophisticated knowledge of the system nor tedious manual parameter tuning is required. To adress task-specic challenges and requirements such as high frequency control, no-overshoot and the control of arbitrary desired trajectories, several theoretical aspects are taken into consideration. To evaluate the theoretical results, the RL controller is applied to a throttle valve simulation aswell as a physical throttle valve system and tested on several control tasks.