paper-with-me

Papers

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models

2019-02-23 · NAACL 2019 6 · Tiancheng Zhao, Kaige Xie, Maxine Eskenazi

Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output vocabulary, e.g. in neural encoder decoders, as the action spaces. Both have their own limitations. This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space from the data. Comprehensive experiments are conducted examining both continuous and discrete action types and two different optimization methods based on stochastic variational inference. Results show that the proposed latent actions achieve superior empirical performance improvement over previous word-level policy gradient methods on both DealOrNoDeal and MultiWoz dialogs. Our detailed analysis also provides insights about various latent variable approaches for policy learning and can serve as a foundation for developing better latent actions in future research.

📄 PDF Abstract BibTeX arXiv:1902.08858

Code (3)

snakeztc/NeuralDialog-LaRL 공식 구현 pytorch
Jupaoqq/Jupaoqq_LaRL pytorch
justinchiu/NeuralDialog pytorch

Tasks

Decision MakingDialogue GenerationDialogue ManagementGoal-Oriented Dialogue SystemsPolicy Gradient MethodsReinforcement LearningVariational Inference

Similar Papers 제목 키워드 기반

Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems

2020-09-21 · Findings of the Association for Computational Linguistics 2020 · Ziming Li, Julia Kiseleva, Maarten de Rijke

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is tim…

DecoderMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONreinforcement-learning+3

Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards

2019-08-27 · Heriberto Cuayáhuitl, Donghyeon Lee, Seonghan Ryu, Sungja Choi 외

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clust…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+3

Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management

2023-02-21 · NeurIPS 2023 11

Reinforcement learning (RL) has shown great promise for developing dialogue management (DM) agents that are non-myopic, conduct rich conversations, and maximize overall user satisfaction. Despite recent developments in R…

Dialogue ManagementDiversityManagementreinforcement-learning+2

Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces

2018-02-11 · Gellért Weisz, Paweł Budzianowski, Pei-Hao Su, Milica Gašić

In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisation task, which attempts to find a polic…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Policy Networks with Two-Stage Training for Dialogue Systems

2016-06-10 · WS 2016 9 · Mehdi Fatemi, Layla El Asri, Hannes Schulz, Jing He 외

In this paper, we propose to use deep policy networks which are trained with an advantage actor-critic method for statistically optimised dialogue systems. First, we show that, on summary state and action spaces, deep Re…

Deep Reinforcement LearningDialogue State TrackingGaussian ProcessesReinforcement Learning+2