相关论文: On-line Active Reward Learning for Policy Optimisa…

Reinforcement learning (RL) has been extensively employed in a wide range of decision-making problems, such as games and robotics. Recently, diffusion policies have shown strong potential in modeling multi-modal behaviors, enabling more…

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 clustered actions instead…

In an era of countless content offerings, recommender systems alleviate information overload by providing users with personalized content suggestions. Due to the scarcity of explicit user feedback, modern recommender systems typically…

Designing effective auxiliary rewards for cooperative multi-agent systems remains challenging, as misaligned incentives can induce suboptimal coordination, particularly when sparse task rewards provide insufficient grounding for coordinated…

Rewards play a crucial role in reinforcement learning. To arrive at the desired policy, the design of a suitable reward function often requires significant domain expertise as well as trial-and-error. Here, we aim to minimize the effort…

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively…

Adaptive interfaces can help users perform sequential decision-making tasks like robotic teleoperation given noisy, high-dimensional command signals (e.g., from a brain-computer interface). Recent advances in human-in-the-loop machine…

There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly…

When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to…

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…

Policy learning (PL) is a module of a task-oriented dialogue system that trains an agent to make actions in each dialogue turn. Imitating human action is a fundamental problem of PL. However, both supervised learning (SL) and reinforcement…

This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents. BCS…

In statistical dialogue management, the dialogue manager learns a policy that maps a belief state to an action for the system to perform. Efficient exploration is key to successful policy optimisation. Current deep reinforcement learning…

End-to-end spoken dialogue models such as GPT-4o-audio have recently garnered significant attention in the speech domain. However, the evaluation of spoken dialogue models' conversational performance has largely been overlooked. This is…

Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their…

Current state-of-the-art neural dialogue models learn from human conversations following the data-driven paradigm. As such, a reliable training corpus is the crux of building a robust and well-behaved dialogue model. However, due to the…

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system…

Combining control engineering with nonparametric modeling techniques from machine learning allows to control systems without analytic description using data-driven models. Most existing approaches separate learning, i.e. the system…

Recent progress on large language models (LLMs) has enabled dialogue agents to generate highly naturalistic and plausible text. However, current LLM language generation focuses on responding accurately to questions and requests with a…

Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with…