Related papers: Learning to Infer User Hidden States for Online Se…
Intent, a critical cognitive notion and mental state, is ubiquitous in human communication and problem-solving. Accurately understanding the underlying intent behind questions is imperative to reasoning towards correct answers. However,…
Understanding the customers' high level shopping intent, such as their desire to go camping or hold a birthday party, is critically important for an E-commerce platform; it can help boost the quality of shopping experience by enabling…
In many engineering systems, proper predictive maintenance and operational control are essential to increase efficiency and reliability while reducing maintenance costs. However, one of the major challenges is that many sensors are used for…
Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assumption made about data is that it does not carry any…
Sequential Recommendation (SRs) that capture users' dynamic intents by modeling user sequential behaviors can recommend closely accurate products to users. Previous work on SRs is mostly focused on optimizing the recommendation accuracy,…
Implicit models are a general class of learning models that forgo the hierarchical layer structure typical in neural networks and instead define the internal states based on an ``equilibrium'' equation, offering competitive performance and…
In this work, we study the problem of actively classifying the attributes of dynamical systems characterized as a finite set of Markov decision process (MDP) models. We are interested in finding strategies that actively interact with the…
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on…
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gather valuable information about the state of the world for…
Recent works have studied *state entropy maximization* in reinforcement learning, in which the agent's objective is to learn a policy inducing high entropy over states visitation (Hazan et al., 2019). They typically assume full…
The traditional approach to POMDPs is to convert them into fully observed MDPs by considering a belief state as an information state. However, a belief-state based approach requires perfect knowledge of the system dynamics and is therefore…
We present an approach for systematically anticipating the actions and policies employed by \emph{oblivious} environments in concurrent stochastic games, while maximizing a reward function. Our main contribution lies in the synthesis of a…
The emerging meta- and multi-verse landscape is yet another step towards the more prevalent use of already ubiquitous online markets. In such markets, recommender systems play critical roles by offering items of interest to the users,…
Abstraction is crucial for effective sequential decision making in domains with large state spaces. In this work, we propose an information bottleneck method for learning approximate bisimulations, a type of state abstraction. We use a deep…
We study planning problems where autonomous agents operate inside environments that are subject to uncertainties and not fully observable. Partially observable Markov decision processes (POMDPs) are a natural formal model to capture such…
We study the offline reinforcement learning (RL) in the face of unmeasured confounders. Due to the lack of online interaction with the environment, offline RL is facing the following two significant challenges: (i) the agent may be…
Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge.…
Device discovery has a great impact on the performance of Bluetooth low energy (BLE). The performance of device discovery is highly related to the advertising mode. BLE has two advertising modes: pseudo-random delay advertising (RDA) and…
Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…
Attention mechanisms excel at learning sequential patterns by discriminating data based on relevance and importance. This provides state-of-the-art performance in advanced generative artificial intelligence models. This paper applies this…