With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared with conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent–environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs’ functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated and provide insights into future directions. Finally, the comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications, such as robotics, autonomous driving, and energy systems.

The sparse representation-based classification (SRC) has been utilized in many applications and is an effective algorithm in machine learning. However, the performance of SRC highly depends on the data distribution. Some existing works proved that SRC could not obtain satisfactory results on uncontrolled data sets. Except the uncontrolled data sets, SRC cannot deal with imbalanced classification either. In this paper, we proposed a model named sparse supervised representation classifier (SSRC) to solve the above-mentioned issues. The SSRC involves the class label information during the test sample representation phase to deal with the uncontrolled data sets. In SSRC, each class has the opportunity to linearly represent the test sample in its subspace, which can decrease the influences of the uncontrolled data distribution. In order to classify imbalanced data sets, a class weight learning model is proposed and added to SSRC. Each class weight is learned from its corresponding training samples. The experimental results based on the AR face database (uncontrolled) and 15 KEEL data sets (imbalanced) with an imbalanced rate ranging from 1.48 to 61.18 prove SSRC can effectively classify uncontrolled and imbalanced data sets.

Multi-view data represented in multiple views contains more complementary information than a single view, whereby multi-view learning explores and utilizes the multi-view data. In general, most existing multi-view learning methods consider the correlation between multiple views. However, the relationship between classes and views which is also important in multi-view learning has never been involved in the existing works. In this paper, we propose a fast and effective multi-view nearest-subspace classifier (MV-NSC) by taking advantage of both the two relationships simultaneously. MV-NSC consists of four main parts: 1) projection residual, 2) view-dependent class separability, 3) view similarity, and 4) final decision. The last part combines the first three parts in one final decision matrix, while the first three parts utilize the information of the multi-view data in various aspects. Our proposed method is evaluated on four benchmark datasets and compared with seven other classifiers including both multi- and single-view algorithms. According to the experimental results, it shows that our proposed method is effective, efficient, and robust in multi-view classification.