Contributions à l'apprentissage par renforcement inverse

Abstract : This thesis, "Contributions à l'apprentissage par renforcement inverse", brings three major contributions to the community. The first one is a method for estimating the feature expectation, a quantity involved in most of state-of-the-art approaches which were thus extended to a batch off-policy setting. The second major contribution is an Inverse Reinforcement Learning algorithm, structured classification for inverse reinforcement learning (SCIRL), which relaxes a standard constraint in the field, the repeated solving of a Markov Decision Process, by introducing the temporal structure (using the feature expectation) of this process into a structured margin classification algorithm. The afferent theoritical guarantee and the good empirical performance it exhibited allowed it to be presentend in a good international conference: NIPS. Finally, the third contribution is cascaded supervised learning for inverse reinforcement learning (CSI) a method consisting in learning the expert's behavior via a supervised learning approach, and then introducing the temporal structure of the MDP via a regression involving the score function of the classifier. This method presents the same type of theoretical guarantee as SCIRL, but uses standard components for classification and regression, which makes its use simpler. This work will be presented in another good international conference: ECML
Document type :
Theses
Complete list of metadatas

Cited literature [71 references]  Display  Hide  Download

https://hal.univ-lorraine.fr/tel-01750440
Contributor : Thèses Ul <>
Submitted on : Thursday, March 29, 2018 - 12:46:16 PM
Last modification on : Tuesday, April 24, 2018 - 1:30:09 PM

File

DDOC_T_2013_0185_KLEIN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-01750440, version 1

Collections

Citation

Edouard Klein. Contributions à l'apprentissage par renforcement inverse. Autre [cs.OH]. Université de Lorraine, 2013. Français. ⟨NNT : 2013LORR0185⟩. ⟨tel-01750440⟩

Share

Metrics

Record views

98

Files downloads

67