Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient

2018-07-02 · Rui Zhao, Volker Tresp

Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and Memory Network structures that leads to an improvement of 7%. The second one is the application of our newly developed TPG methods, which improves the performance additionally by around 5% and, even more importantly, helps produce more convincing utterances.

📄 PDF Abstract BibTeX arXiv:1807.00737

Code (1)

ruizhaogit/GuessWhat-TemperedPolicyGradient 공식 구현 pytorch

Tasks

Deep Reinforcement LearningPolicy Gradient MethodsReinforcement Learning Reinforcement Learning (RL)Visual Dialog

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog

2018-05-08 · WS 2018 7 · Jiaping Zhang, Tiancheng Zhao, Zhou Yu

Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Extensive research has focused on vision-t…

Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog

2019-08-28 · IJCNLP 2019 11 · Ryuichi Takanobu, Hanlin Zhu, Minlie Huang

Dialog policy decides what and how a task-oriented dialog system will respond, and plays a vital role in delivering effective conversations. Many studies apply Reinforcement Learning to learn a dialog policy with the rew…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient

2017-12-07 · Li Zhou, Kevin Small, Oleg Rokhlenko, Charles Elkan

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog tra…

Decoder Goal-Oriented Dialog Offline RL Reinforcement Learning+1

Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts

2019-07-24 · Yen-Wei Chang, Wen-Hsiao Peng

This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generate…

Imitation Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning

2023-05-23 · Xiao Yu, Maximillian Chen, Zhou Yu

Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such…

Language Modeling Language Modelling Large Language Model