相关论文: Efficient Reinforced Feature Selection via Early S…

Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and…

As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…

The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion; however, this is…

Multi-view unsupervised feature selection has been proven to be efficient in reducing the dimensionality of multi-view unlabeled data with high dimensions. The previous methods assume all of the views are complete. However, in real…

Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy parameterization is inherently unimodal, limiting its ability to model complex multimodal…

Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient…

In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named…

Recent advances in both machine learning and Internet-of-Things have attracted attention to automatic Activity Recognition, where users wear a device with sensors and their outputs are mapped to a predefined set of activities. However, few…

Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Feature Selection (FS) plays an important role in learning and classification tasks. The object of FS is to select the relevant and non-redundant features. Considering the huge amount number of features in real-world applications, FS…

The explosion of data in recent years has generated an increasing need for new analysis techniques in order to extract knowledge from massive datasets. Machine learning has proved particularly useful to perform this task. Fully automatized…

Click-through-rate (CTR) prediction plays an important role in online advertising and ad recommender systems. In the past decade, maximizing CTR has been the main focus of model development and solution creation. Therefore, researchers and…

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel,…

Most reinforcement learning practitioners evaluate their policies with online Monte Carlo estimators for either hyperparameter tuning or testing different algorithmic design choices, where the policy is repeatedly executed in the…

Feature interaction modeling is crucial for deep recommendation models. A common and effective approach is to construct explicit feature combinations to enhance model performance. However, in practice, only a small fraction of these…

Feature selection in high-dimensional genomic data ($d \gg n$) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches either require manual threshold specification (mRMR, stability selection), produce…

Many-Objective Feature Selection (MOFS) approaches use four or more objectives to determine the relevance of a subset of features in a supervised learning task. As a consequence, MOFS typically returns a large set of non-dominated…

As a key stage of Recommender Systems (RSs), Multi-Task Fusion (MTF) is responsible for merging multiple scores output by Multi-Task Learning (MTL) into a single score, finally determining the recommendation results. Recently, Reinforcement…