Compressed prompts aid instruction-tuned language models (LMs) in overcoming context window limitations and reducing computational costs. Existing methods, which primarily based on training embeddings, face various challenges associated with interpretability, the fixed number of embedding tokens, reusability across different LMs, and inapplicability when interacting with black-box APIs. This study proposes prompt compression with reinforcement learning (PCRL), which is a discrete prompt compression method that addresses these issues. The proposed PCRL method utilizes a computationally efficient policy network that edits prompts directly. The training approach employed in the proposed PCRLs can be applied flexibly to various types of LMs, including both decoder-only and encoder-decoder architecture and it can be trained without gradient access to the LMs or labeled data. The proposed PCRL achieves an average reduction of 24.6% in terms of the token count across various instruction prompts while maintaining sufficient performance. In addition, we demonstrate that the learned policy can be transferred to larger LMs, and through a comprehensive analysis, we explore the token importance within the prompts.

Rainfall is a complex phenomenon with high spatiotemporal variability. Identification of homogeneous rainfall zones to better analyse the rainfall intensity and extent is of vital significance for water resources management and mitigation of potential hazards from extreme events, i.e. droughts and floods. Appropriate zoning of homogeneous rainfall regions may give better understanding of rainfall patterns by resolving small scale variations. Although homogeneous rainfall zones have been established at country scale based on climatological mean behaviour, there has been little attempt to identify zones over broader scale with consistently homogeneous rainfall variability. This study employed K-means and Hierarchical clustering methods to establish homogeneous rainfall zones in the East Asia monsoon region (20°N–50°N, 103°E–149°E) using 30 years (1978–2007) monthly rainfall data at 0.5° grid resolution. Various cluster validation indices were used to assess the optimal number of homogeneous rainfall zones. The comparison of K-means and Hierarchical clustering showed that although both methods were able to define the homogeneous rainfall zones well with spatial contiguity, the K-means clustering outperformed the Hierarchical clustering in identifying more distinct zones with diverse rainfall characteristics. Mann-Kendall and linear regression tests were used for seasonal and annual rainfall trend analysis in the homogeneous rainfall zones. The study revealed that the region experiences distinct rainfall regimes over different zones. Furthermore, significant increasing and decreasing trends were observed over different zones with strong seasonal variation that indicate the aggravated stress of climate induced disasters, i.e. droughts and floods over the East Asia monsoon region.

In general, the analysis of microarray data requires two steps: feature selection and classification. From a variety of feature selection methods and classifiers, it is difficult to find optimal ensembles composed of any feature-classifier pairs. This paper proposes a novel method based on the evolutionary algorithm (EA) to form sophisticated ensembles of features and classifiers that can be used to obtain high classification performance. In spite of the exponential number of possible ensembles of individual feature-classifier pairs, an EA can produce the best ensemble in a reasonable amount of time. The chromosome is encoded with real values to decide the weight for each feature-classifier pair in an ensemble. Experimental results with two well-known microarray datasets in terms of time and classification rate indicate that the proposed method produces ensembles that are superior to individual classifiers, as well as other ensembles optimized by random and greedy strategies.

Game companies avoid sharing their game data with external researchers. Only a few research groups have been granted limited access to game data so far. The reluctance of these companies to make data publicly available limits the wide use and development of data mining techniques and artificial intelligence research specific to the game industry. In this work, we developed and implemented an international competition on game data mining using commercial game log data from one of the major game companies in South Korea: NCSOFT. Our approach enabled researchers to develop and apply state-of-the-art data mining techniques to game log data by making the data open. For the competition, data were collected from Blade & Soul, an action role-playing game, from NCSOFT. The data comprised approximately 100 GB of game logs from 10,000 players. The main aim of the competition was to predict whether a player would churn and when the player would churn during two periods between which the business model was changed to a free-to-play model from a monthly subscription. The results of the competition revealed that highly ranked competitors used deep learning, tree boosting, and linear regression.

Deep Reinforcement Learning (DRL) allows agents to learn strategies to solve complex tasks. It has been applied to solve various problems such as natural language processing, games, etc. However, it is still difficult to apply DRL to certain real-world problems because each action is not predictable, and we cannot know why the results are coming out. For this reason, a technology called eXplainable Artificial Intelligence (XAI) has been recently developed. As this technology shows a visualization of the AI process, people can easily understand the results of AI. In this paper, we proposed to use Grad-CAM, one of the XAI techniques, when we visualize the behaviors of AI players trained by DRL. Our experimental results show which part of the input state is focused on when one well-trained agent takes action.