Structured prediction with reinforcement learning

By Francis Maes, Ludovic Denoyer, Patrick Gallinari. 2009

34 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yoshua Bengio
2. Yejin Choi
3. Mohit Bansal
4. Jianfeng Gao
5. Kyunghyun Cho
6. Jason Aaron Edward Weston
7. Sergey Levine
8. Quoc V. Le

In Information Systems

1. Joelle Pineau
2. Ryan J. Lowe
3. Aaron C. Courville
4. Yoshua Bengio
5. Yejin Choi
6. Nicolas Usunier
7. Prithviraj Ammanabrolu
8. Sean Welleck

In Natural Language Processing

1. Yejin Choi
2. Kyunghyun Cho
3. Jason Aaron Edward Weston
4. Mohit Bansal
5. Jianfeng Gao
6. Yoshua Bengio
7. Hannaneh Hajishirzi
8. Luke S. Zettlemoyer

In Reinforcement Learning

1. Yoshua Bengio
2. Zeming Lin
3. Nicolas Usunier
4. Gabriel Synnaeve
5. Anirudh Goyal
6. Joelle Pineau
7. Aaron C. Courville
8. Yejin Choi

Citations in the corpus

• An Actor-Critic Algorithm for Sequence Prediction (2016, methodology): “Standard value-based RL algorithms like SARSA and OLPOMDP have also been applied to structured prediction (Maes et al., 2009).”
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks (2016, methodology): “This reduction was previously proposed in the context of structured prediction by Maes et al. [17], who proved that an optimal policy in this new MDP has the same cumulative reward as an optimal policy in the original MDP.”
• Quark: Controllable Text Generation with Reinforced Unlearning (2022, methodology): “Previous works have used RL techniques in a wide range of classical NLP applications, such as named entity recognition [41], semantic parsing [89], dependency parsing [79], constituency parsing [16], part-of-speech tagging [6], and information extraction [48].”
• VISUAL ATTENTION (2014, unknown): “Our approach of learning by maximizing variational lower bound is equivalent to the reinforcement learning procedure used in RAM and is related to the work of Maes et al. (2009) who showed how reinforcement learning can be used to tackle general structured prediction problems.”