Synonyms
Definition
Reward shaping is a technique inspired by animal training where supplemental rewards are provided to make a problem easier to learn. There is usually an obvious natural reward for any problem. For games, this is usually a win or loss. For financial problems, the reward is usually profit. Reward shaping augments the natural reward signal by adding additional rewards for making progress toward a good solution.
Motivation and Background
Reward shaping is a method for engineering a reward function in order to provide more frequent feedback on appropriate behaviors. It is most often discussed in the reinforcement learning framework. Providing feedback is crucial during early learning so that promising behaviors are tried early. This is necessary in large domains, where reinforcement signals may be few and far between.
A good example of such a problem is chess. The objective of chess is to win a match, and an appropriate reinforcement...
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsRecommended Reading
Koenig S, Simmons RG (1996) The effect of representation and knowledge on goal directed exploration with reinforcement-learning algorithms. Mach Learn 22(1–3):227–250
Mataric MJ (1994) Reward functions for accelerated learning. In: International conference on machine learning, New Brunswick. Morgan Kaufmann, San Francisco, pp 181–189
Ng AY, Harada D, Russell S (1999) Policy invariance under reward transformations: theory and application to reward shaping. In: Machine learning, proceedings of the sixteenth international conference, Bled. Morgan Kaufmann, San Francisco, pp 278–287
Randlov J, Alstrom P (1998) Learning to drive a bicycle using reinforcement learning and shaping. In: Proceedings of the fifteenth international conference on machine learning, Madison. Morgan Kaufmann, San Francisco
Wiewiora E (2003) Potential-based shaping and Q-value initialization are equivalent. J Artif Intell Res 19: 205–208
Wiewiora E, Cottrell G, Elkan C (2003) Principled methods for advising reinforcement learning agents. In: Machine learning, proceedings of the twentieth international conference, Washington, DC. AAAI Press, Menlo Park, pp 792–799
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
Wiewiora, E. (2017). Reward Shaping. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_966
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_966
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering