#### Filter Results:

- Full text PDF available (70)

#### Publication Year

2008

2018

- This year (3)
- Last 5 years (39)
- Last 10 years (94)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

Learn More

- Matthieu Geist, Olivier Pietquin
- J. Artif. Intell. Res.
- 2010

Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novelâ€¦ (More)

- Lucie Daubigney, Matthieu Geist, Senthilkumar Chandramohan, Olivier Pietquin
- IEEE Journal of Selected Topics in Signalâ€¦
- 2012

Reinforcement learning is now an acknowledged approach for optimizing the interaction strategy of spoken dialogue systems. If the first considered algorithms were quite basic (like SARSA), recentâ€¦ (More)

Designing dialog policies for voice-enabled interfaces is a tailoring job that is most often left to natural language processing experts. This job is generally redone for every new dialog taskâ€¦ (More)

- Edouard Klein, Matthieu Geist, Bilal Piot, Olivier Pietquin
- NIPS
- 2012

This paper adresses the inverse reinforcement learning (IRL) problem, that is inferring a reward for which a demonstrated expert behavior is optimal. We introduce a new algorithm, SCIRL, whoseâ€¦ (More)

Spoken Dialogue Systems (SDS) are systems which have the ability to interact with human beings using natural language as the medium of interaction. A dialogue policy plays a crucial role inâ€¦ (More)

- Olivier Pietquin, CÃ©dric Boidin, +14 authors Kai Zhi Yu
- Springer New York
- 2012

LSTD is a popular algorithm for value function approximation. Whenever the number of features is larger than the number of samples, it must be paired with some form of regularization. In particular,â€¦ (More)

The dilemma between exploration and exploitation is an important topic in reinforcement learning (RL). Most successful approaches in addressing this problem tend to use some uncertainty informationâ€¦ (More)

- Edouard Klein, Bilal Piot, Matthieu Geist, Olivier Pietquin
- ECML/PKDD
- 2013

This paper considers the Inverse Reinforcement Learning (IRL) problem, that is inferring a reward function for which a demonstrated expert policy is optimal. We propose to break the IRL problem downâ€¦ (More)

- Matthieu Geist, Olivier Pietquin
- IEEE Transactions on Neural Networks and Learningâ€¦
- 2013

Reinforcement learning (RL) is a machine learning answer to the optimal control problem. It consists of learning an optimal control policy through interactions with the system to be controlled, theâ€¦ (More)