### Abstract

We study the problem of an apprentice learning to behave in an environment with an unknown reward function by observing the behavior of an expert. We follow on the work of Abbeel and Ng [1] who considered a framework in which the true reward function is assumed to be a linear combination of a set of known and observable features. We give a new algorithm that, like theirs, is guaranteed to learn a policy that is nearly as good as the expert's, given enough examples. However, unlike their algorithm, we show that ours may produce a policy that is substantially better than the expert's. Moreover, our algorithm is computationally faster, is easier to implement, and can be applied even in the absence of an expert. The method is based on a game-theoretic view of the problem, which leads naturally to a direct application of the multiplicative-weights algorithm of Freund and Schapire [2] for playing repeated matrix games. In addition to our formal presentation and analysis of the new algorithm, we sketch how the method can be applied when the transition function itself is unknown, and we provide an experimental demonstration of the algorithm on a toy video-game environment.

Original language | English (US) |
---|---|

Title of host publication | Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference |

State | Published - Dec 1 2009 |

Event | 21st Annual Conference on Neural Information Processing Systems, NIPS 2007 - Vancouver, BC, Canada Duration: Dec 3 2007 → Dec 6 2007 |

### Publication series

Name | Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference |
---|

### Other

Other | 21st Annual Conference on Neural Information Processing Systems, NIPS 2007 |
---|---|

Country | Canada |

City | Vancouver, BC |

Period | 12/3/07 → 12/6/07 |

### All Science Journal Classification (ASJC) codes

- Information Systems

## Fingerprint Dive into the research topics of 'A game-theoretic approach to apprenticeship learning'. Together they form a unique fingerprint.

## Cite this

*Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference*(Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).