GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems

By Youngsoo Jang, Jongmin Lee, Kee-Eung Kim. 2022

46 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

1. Jason Phang
2. Samuel R. Bowman
3. Ethan Perez
4. Angelica Chen
5. Sam Bowman
6. Rasika Bhalerao
7. Sergey Levine
8. Tomasz Korbak

In Reinforcement Learning

1. Ilya Kostrikov
2. Mengjiao Yang
3. Tomasz Korbak
4. Sergey Levine
5. C. L. Buckley
6. Ethan Perez
7. Charles Burton Snell
8. Pieter Abbeel

Citations in the corpus

• Pretraining Language Models with Human Preferences (2023, methodology): “However, offline RL techniques were recently used for finetuning pretrained LMs to be aligned with human preferences in dialog tasks (Jaques et al., 2020; Jang et al., 2022; Snell et al., 2022).”
• Offline RL for Natural Language Generation with Implicit Language Q Learning (2022, methodology): “The most closely related to our work are those methods based on approximate dynamic programming [12, 13, 11, 30].”