home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!pipex!bnr.co.uk!uknet!cam-eng!dsl!ttj10
- From: ttj10@eng.cam.ac.uk (Tim Jervis)
- Newsgroups: sci.engr.control
- Subject: Technical report: real pole balancing
- Message-ID: <TTJ10.92Dec22123522@dsl.eng.cam.ac.uk>
- Date: 22 Dec 92 17:35:22 GMT
- Sender: ttj10@eng.cam.ac.uk (T.T. Jervis)
- Organization: Engineering Department, Cambridge University, England.
- Lines: 61
- Nntp-Posting-Host: dsl.eng.cam.ac.uk
-
- The following technical report is available via the Cambridge
- University ftp archive svr-ftp.eng.cam.ac.uk. Instructions for
- retrieval from the archive follow the summary.
-
- ------------------------------------------------------------------------------
-
- Pole Balancing on a Real Rig using a
- Reinforcement Learning Controller
-
-
- Timothy Jervis and Frank Fallside
-
-
- Cambridge University Engineering Department
- Cambridge CB2 1PZ, England
-
-
-
- Abstract
-
- In 1983, Barto, Sutton and Anderson~\cite{Barto83} published details
- of an adaptive controller which learnt to balance a simulated inverted
- pendulum. This {\em reinforcement learning} controller balanced the
- pendulum as a by-product of avoiding a cost signal delivered to the
- controller when the pendulum fell over. This paper describes their
- controller learning to balance a real inverted pendulum. As far as
- the authors are aware, this is the first example of a reinforcement
- learning controller being applied to a real inverted pendulum learning
- in real time.
-
- The results show that the controller was able to improve its
- performance as it learnt, and that the task is computationally
- tractable. However, the implementation was not straightforward.
- Although some of the controller's parameters were tuned automatically
- by learning, some were not and had to be carefully set for successful
- control. This limits the usefulness of this kind of learning
- controller to small problems which are likely to be better controlled
- by other means. Before a learning controller can tackle more difficult
- problems, a more powerful learning scheme has to be found.
-
- ------------------------------------------------------------------------------
-
- FTP INSTRUCTIONS
-
- unix> ftp svr-ftp.eng.cam.ac.uk
- Name: anonymous
- Password: (your_userid@your_site)
- ftp> cd reports
- ftp> binary
- ftp> get jervis_tr115.ps.Z
- ftp> quit
- unix> uncompress jervis_tr115.ps.Z
- unix>
-
- If "ftp svr-ftp.eng.cam.ac.uk" does not work,
- you might try "ftp 129.169.24.20".
- --
- _/_/_/_/_/ _/ _/ _/ Cambridge University
- _/ _/ _/_/ _/_/ Engineering Department,
- _/ _/ _/ _/ _/ Trumpington Street,
- Cambridge CB2 1PZ, England
-