The ambition of this page is to collect RL success stories. By "success story" we mean an application of RL methods to a substantial and difficult problem domain that is of independent interest (to some community). Yes, this is vague and if that leads to a longer list than otherwise, that may be ok.

---

Jump to successes in: [[#RoboticS][Robotics]], [[#ControL][Control]], [[#OperationsresearcH][Operations Research]], [[

#GameS][Games]], [[#HcI][Human-Computer Interaction]], [[#EcO][Economics/Finance]], [[#CoS][Complex Simulation]]

-------------

Robotics

1. (Quadruped Gait Control) Policy Gradient Reinforcement Learning for Fast Quadrupedal Locomotion by Nate Kohl and Peter Stone
2. (Quadruped Ball Acquisition) Learning Ball Acquisition on a Physical Robot by Peggy Fidelman and Peter Stone

(__Air Hockey__) [[http://www.cc.gatech.edu/projects/Learning_Research/][Learning from Observation U

sing Primitives]], and particularly the movie of a [[http://www.cc.gatech.edu/project/Learning_Research/mpeg/hockeyfullsmall.avi][humanoid robot playing air hockey]]. An example [[http://www.cc.gatech.edu/projects/Learning_Research/Docs/dbent_iros02.pdf][paper]].

(__Active Sensing__) [[http://www.cs.washington.edu/robotics/abstracts/active-sensing-iros-04.abstra

ct.html][Active Sensing Using Reinforcement Learning]] by Cody Kwok and Dieter Fox.

#ControL

* %RED%Control%ENDCOLOR%

1 (__Helicopter control__) [[http://www.robotics.stanford.edu/~ang/papers/iser04-invertedflight.pdf][I

nverted autonomous helicopter flight via reinforcement learning]], by Andrew Y. Ng, Adam Coates, Mark Diel, Varun Gana

pathi, Jamie Schulte, Ben Tse, Eric Berger and Eric Liang. In International Symposium on Experimental Robotics, 2004.

1 (__Helicopter control__) [[http://www.ri.cmu.edu/pubs/pub_3791.html][Autonomous helicopter control u

sing Reinforcement Learning Policy Search Methods]], by J.A. Bagnell and J. Schneider. In Proceedings of the Internati

onal Conference on Robotics and Automation, 2001.

#OperationsresearcH

* %RED%Operations Research%ENDCOLOR%

1 (__Pricing__) [[http://www.stanford.edu/~bvr/psfiles/GM-pricing.pdf][Opportunities and Challenges in

Using Online Preference Data for Vehicle Pricing: A Case Study at General Motors]] by P. Rusmevichientong, J. A. Sali

sbury, L. T. Truss, B. Van Roy, and P. W. Glynn.

1 (__Vehicle Routing__) [[http://web.engr.oregonstate.edu/~proper/AAAI04SProper.pdf][Scaling Average-r

eward Reinforcement Learning for Product Delivery]] by S. Proper and P. Tadepalli.

#GameS

* %RED%Games%ENDCOLOR%

1 (__Backgammon__) [[http://www.research.ibm.com/massive/tdl.html][Temporal difference learning and TD

-Gammon]] by Gerald Tesauro, Communications of the ACM, 38(3), March 1995.

1 (__Solitaire__) [[http://www.stanford.edu/~bvr/psfiles/solitaire.pdf][Solitaire: Man Versus Machine]

], by X. Yan, P. Diaconis, P. Rusmevichientong, and B. Van Roy, to appear in Advances in Neural Information Processing

Systems 17, MIT Press, 2005.

1 (__Chess__) [[http://www.syseng.anu.edu.au/lsg/knightcap.html][The KnightCap program]], which went f

rom a rating of 1600 to a rating of 2100 by altering its heuristic evaluation function using TD-lambda. [[http://cite

seer.ist.psu.edu/6262.html][CiteSeer]] has a link to the paper.

1 (__Checkers__) [[http://www.cs.ualberta.ca/~jonathan/Papers/Papers/td.ps][Temporal Difference Learni

ng Applied to a High-Performance Game-Playing Program]] by Jonathan Schaeffer, Markian Hlynka, and Vili Jussila, Inter

national Joint Conference on Artificial Intelligence (IJCAI), pp. 529-534, 2001..

#HcI

* %RED%Human-Computer Interaction%ENDCOLOR%

1 (__Spoken Dialogue Systems__) [[http://www.eecs.umich.edu/~baveja/Papers/RLDSjair.pdf][Optimizing D

ialogue Management with Reinforcement Learning: Experiments with the NJFun System]]. S. Singh, D. Litman, M. Kearns an

d M. Walker. In Journal of Artificial Intelligence Research (JAIR), Volume 16, pages 105-133, 2002

1 (__Software Agent in MOOs__) [[http://www.eecs.umich.edu/~baveja/Papers/CobotNIPS01.pdf][Cobot: A So

cial Reinforcement Learning Agent]]. C. Isbell, C. Shelton, M. Kearns, S. Singh, and P. Stone (2002). In Proceedings o

f Neural Information Processing Systems 14 (NIPS), pp. 1393-1400.

#EcO

* %RED%Economics/Finance%ENDCOLOR%

1 (__Trading__) Learning to Trade via Direct Reinforcement. John Moody and Matthew Saffell, IEEE Trans

actions on Neural Networks, Vol 12, No 4, July 2001.

#CoS

* %RED%Complex Simulation%ENDCOLOR%

1 (__Robot_Soccer__) [[http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/ICML2001.pdf][Scaling Re

inforcement Learning toward RoboCup Soccer]], by Peter Stone and Richard S. Sutton, Proceedings of the Eighteenth Inte

rnational Conference on Machine Learning, pp. 537–544, Morgan Kaufmann, San Francisco, CA, 2001.

#MkT

* %RED%Marketing%ENDCOLOR%

1 (__Targeted_Marketing__) [[http://www.research.ibm.com/people/n/nabe/kdd04AVAS.pdf][Cross Channel Op

timized Marketing by Reinforcement Learning]], by Naoki Abe, Naval Verma, Chid Apte and Robert Schroko, Proceedings of

the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2004.