Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook
Author:
Preprint
Abstract
In recent years, reinforcement learning and bandits have transformed a wide range of real-world applications including healthcare, finance, recommendation systems, robotics, and last but not least, the speech and natural language processing. While most speech and language applications of reinforcement learning algorithms are centered around improving the training of deep neural networks with its flexible optimization properties, there are still many grounds to explore to utilize the benefits of reinforcement learning, such as its reward-driven adaptability, state representations, temporal structures and generalizability. In this survey, we present an overview of recent advancements of reinforcement learning and bandits, and discuss how they can be effectively employed to solve speech and natural language processing problems with models that are adaptive, interactive and scalable.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- A survey of uncertainty in deep neural networksArtificial Intelligence Review, 2023
- Deep Reinforcement Learning for On-line Dialogue State Tracking2023
- Survey on reinforcement learning for language processingArtificial Intelligence Review, 2022
- Deep reinforcement learning in computer vision: a comprehensive surveyArtificial Intelligence Review, 2021
- A survey of inverse reinforcement learning: Challenges, methods and progressArtificial Intelligence, 2021
- Reinforcement Learning in Economics and FinanceComputational Economics, 2021
- Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL2021
- Multi-armed bandit problem with known trendNeurocomputing, 2016
- Cooperative Multi-Agent Learning: The State of the ArtAutonomous Agents and Multi-Agent Systems, 2005
- Asymptotically efficient adaptive allocation rulesAdvances in Applied Mathematics, 1985