The ambition of this page is to become a comprehensive list of available demos of RL.

Andrew Ng's Helicopter Videos

• Inverted Flight
• Manouver (Vertical Triangle with 180 Pirouettes)
• Manouver (Noise in Circle)
• Manouver (Vertical Rectangle with 360 Pirouettes)

Stefan Schaal, Jan Peters, etal.

• CLMC's Movie Page

Drew Bagnell, Sham Kakade, Andrew Ng, Jeff Schneider: Various demos %BR% (*Original Souce*: Drew's [[http://www.mindchil

d.org/][personal page]])

                1 [[http://www.autonlab.org/autonweb/animations/GoodWalk-demo.mov][Simulated Walking Robot]]

                1 [[http://gibbs.sp.cs.cmu.edu/~dbagnell/tetrisGrad.avi][Tetris Playing]] (Algorithm: Reinforce)

                1 [[http://gibbs.sp.cs.cmu.edu/~dbagnell/Heli.mov][Helicopter Control]]

        * [[http://www.cc.gatech.edu/projects/Learning_Research/][Darrin Bentivegna]]

                1 [[http://www.cc.gatech.edu/projects/Learning_Research/mpeg/hockeyfullsmall.avi][Humanoid robot playing air hocke

y]].

        * [[http://www.cs.utexas.edu/~pstone/][Peter Stone]] and [[http://www.cs.utexas.edu/~nate/][Nate Kohl]]'s Learning AIBO Ga

it Control Videos (mpg format) %BR% (*Original Source*: Peter Stone's [[http://www.cs.utexas.edu/users/AustinVilla/?p=research/lea

rned_walk][Learning to Walk Page]])

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-walk/experiment-overview.mpg][Experimental Setup]]

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-walk/initial.mpg][Initial Gait]]

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-walk/training-1.mpg][Training Process]]

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-walk/finished.mpg][Learned Gait]]

        * [[http://www.cs.utexas.edu/~pstone/][Peter Stone]] and [[http://www.cs.utexas.edu/~peggy/][Peggy Fidelman]]'s Learning A

IBO Ball Control Videos (mpg format) %BR% (*Original Source*: Peter Stone's [[http://www.cs.utexas.edu/users/AustinVilla/?p=resear

ch/learned_acquisition][Learning to Acquire the Ball Page]])

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-acquisition/before.mp4][Initial Policy]]

                1 [[http://www.cs.utexas.edu/users/AustinVilla/legged/learned-acquisition/after.mp4][Best Learned Policy]]

        * [[http://www.fe.dis.titech.ac.jp/~gen/][Hajime Kimura]]: Real Robot Demos %BR% (*Original Source*: Hajime's [[http://www

.fe.dis.titech.ac.jp/~gen/RealRobots/RealRobots.html][web page]])

                1 [[http://www.fe.dis.titech.ac.jp/~gen/RealRobots/ROBOT_As.mpg][Walking Hand (small)]]

                1 [[http://www.fe.dis.titech.ac.jp/~gen/RealRobots/ROBOT_A.mpg][Walking Hand (large)]]

                1 [[http://www.fe.dis.titech.ac.jp/~gen/RealRobots/ROBOT_Bs.mpg][(Pushing flexible assembly (small)]]

                1 [[http://www.fe.dis.titech.ac.jp/~gen/RealRobots/ROBOT_B.mpg][Pushing flexible assembly (large)]]

        * [[http://www.fe.dis.titech.ac.jp/~gen/][Hajime Kimura]]'s Java Demo of [[http://www.fe.dis.titech.ac.jp/~gen/robot/robod

emo.html][Simulated 2 jointed robot]]

--More--* [[http://www.eecs.umich.edu/~baveja][Satinder Singh]]'s Java Demo of [[http://www.eecs.umich.edu/~baveja/Demo.html][Simu

lated Dynamic Channel Assignment in Cellular Telephones]]

        * [[http://www.cs.utexas.edu/~pstone/][Peter Stone]], [[http://www.cs.ualberta.ca/~sutton/][Rich Sutton]], and [[http://ww

w.cs.utexas.edu/~kuhlmann/][Greg Kuhlmann]]'s Simulated Robosoccer Keepaway Task %BR% (*Original Source*: Peter Stone's [[http://w

ww.cs.utexas.edu/users/AustinVilla/sim/keepaway/][Keepaway Page]])

                1 3 %$\times$% 2 keepaway

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/hand360.swf][Hand Coded]] policy's perform

ance

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/hold360.swf][Always Hold]] policy's perfor

mance

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/rand360.swf][Random]] policy's performance

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/learn360.swf][Learned]] policy's performan

ce

                1 4 %$\times$% 3 keepaway

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/rand4v3.swf][Random]] policy's performance

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/learn4v3.swf][Learned]] policy's performan

ce

                1 5 %$\times$% 4 keepaway

                        1 [[http://www.cs.utexas.edu/users/AustinVilla/sim/keepaway/swf/learn5v4.swf][Learned]] policy's performan

ce