Related papers: Dialogue Evaluation with Offline Reinforcement Lea…

Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a…

Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally…

Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities. In this paper, we survey…

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

In this paper, we argue that the paradigm commonly adopted for offline evaluation of sequential recommender systems is unsuitable for evaluating reinforcement learning-based recommenders. We find that most of the existing offline evaluation…

Research and development on conversational recommender systems (CRSs) critically depends on sound and reliable evaluation methodologies. However, the interactive nature of these systems poses significant challenges for automatic evaluation.…

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained…

The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates…

Design of dialogue systems has witnessed many advances lately, yet acquiring huge set of data remains an hindrance to their fast development for a new task or language. Besides, training interactive systems with batch data is not…

Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system,…

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains. To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Evaluation), a public…

Evaluation of open-domain dialogue systems is highly challenging and development of better techniques is highlighted time and again as desperately needed. Despite substantial efforts to carry out reliable live evaluation of systems in…

Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep…

Automatic dialogue evaluation plays a crucial role in open-domain dialogue research. Previous works train neural networks with limited annotation for conducting automatic dialogue evaluation, which would naturally affect the evaluation…

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where…

We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong,…

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current…

Dialog response ranking is used to rank response candidates by considering their relation to the dialog history. Although researchers have addressed this concept for open-domain dialogs, little attention has been focused on task-oriented…

Task-oriented dialogue systems (TDSs) are assessed mainly in an offline setting or through human evaluation. The evaluation is often limited to single-turn or is very time-intensive. As an alternative, user simulators that mimic user…