Related papers: Dialogue Evaluation with Offline Reinforcement Lea…

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction with the environment,…

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…

On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be…

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 RL and language…

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models…

Conversational recommender systems (CRS) are interactive agents that support their users in recommendation-related goals through multi-turn conversations. Generally, a CRS can be evaluated in various dimensions. Today's CRS mainly rely on…

Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typically rely on stronger supervisors for annotating critique…

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen…

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

The performance of a task-completion dialogue agent usually affects the user experience: when the conversation system yields an unreasonable response, users may feel dissatisfied. Besides, early termination often occurs in disappointing…

Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…

Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space…

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to…

Automated metrics such as BLEU are widely used in the machine translation literature. They have also been used recently in the dialogue community for evaluating dialogue response generation. However, previous work in dialogue response…

Imagine if AI decision-support tools not only complemented our ability to make accurate decisions, but also improved our skills, boosted collaboration, and elevated the joy we derive from our tasks. Despite the potential to optimize a broad…

The task-oriented spoken dialogue system (SDS) aims to assist a human user in accomplishing a specific task (e.g., hotel booking). The dialogue management is a core part of SDS. There are two main missions in dialogue management: dialogue…