Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm
Nowadays, the current neural network models of dialogue generation(chatbots) show great promise for generating answers for chatty agents. But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes. Modelling a dialogue's future direction is critical for generating coherent, interesting dialogues, a need that has led traditional NLP dialogue models that rely on reinforcement learning. In this article, we explain how to combine these objectives by using deep reinforcement learning to predict future rewards in chatbot dialogue. The model simulates conversations between two virtual agents, with policy gradient methods used to reward sequences that exhibit three useful conversational characteristics: the flow of informality, coherence, and simplicity of response (related to forward-looking function). We assess our model based on its diversity, length, and complexity with regard to humans. In dialogue simulation, evaluations demonstrated that the proposed model generates more interactive responses and encourages a more sustained successful conversation. This work commemorates a preliminary step toward developing a neural conversational model based on the long-term success of dialogues.
Code (0)
등록된 구현이 없습니다.
Tasks
ChatbotDeep Reinforcement LearningDialogue GenerationDiversityPolicy Gradient Methodsreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning
Offline reinforcement learning aims to utilize datasets of previously gathered environment-action interaction records to learn a policy without access to the real environment. Recent work has shown that offline reinforce…
D4RLOff-policy evaluationOpenAI Gymreinforcement-learning+1Group Sequence Policy Optimization
This paper introduces Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant reinforcement learning algorithm for training large language models. Unlike previous algorithms that adopt token-leve…
Reinforcement LearningPolicy Learning for Malaria Control
Sequential decision making is a typical problem in reinforcement learning with plenty of algorithms to solve it. However, only a few of them can work effectively with a very small number of observations. In this report, …
Bayesian OptimizationDecision MakingQ-Learningreinforcement-learning+3Proximal Policy Optimization and its Dynamic Version for Sequence Generation
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in…
ChatbotModel Optimizationreinforcement-learningReinforcement Learning+1CoMPS: Continual Meta Policy Search
We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforc…
Continual Learningcontinuous-controlContinuous ControlMeta-Learning+5