Search

Driven by the rapid growth of machine learning, recent advances in game artificial intelligence (AI) have significantly impacted productivity across various gaming genres. Reward design plays a pivotal role in training game AI models, wherein researchers implement concepts of specific reward functions. However, despite the presence of AI, the reward design process predominantly remains in the domain of human experts, as it is heavily reliant on their creativity and engineering skills. Therefore, this paper proposes ChatPCG, a large language model (LLM)-driven reward design framework.It leverages human-level insights, coupled with game expertise, to generate rewards tailored to specific game features automatically. Moreover, ChatPCG is integrated with deep reinforcement learning, demonstrating its potential for multiplayer game content generation tasks. The results suggest that the proposed LLM exhibits the capability to comprehend game mechanics and content generation tasks, enabling tailored content generation for a specified game. This study not only highlights the potential for improving accessibility in content generation but also aims to streamline the game AI development process., Comment: 4 pages, 2 figures, accepted at IEEE Conference on Games 2024

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. Our code is accessible at https://github.com/nenomigami/PromptCompressor.

The balance of game content significantly impacts the gaming experience. Unbalanced game content diminishes engagement or increases frustration because of repetitive failure. Although game designers intend to adjust the difficulty of game content, this is a repetitive, labor-intensive, and challenging process, especially for commercial-level games with extensive content. To address this issue, the game research community has explored automated game balancing using artificial intelligence (AI) techniques. However, previous studies have focused on limited game content and did not consider the importance of the generalization ability of playtesting agents when encountering content changes. In this study, we propose RaidEnv, a new game simulator that includes diverse and customizable content for the boss raid scenario in MMORPG games. Additionally, we design two benchmarks for the boss raid scenario that can aid in the practical application of game AI. These benchmarks address two open problems in automatic content balancing, and we introduce two evaluation metrics to provide guidance for AI in automatic content balancing. This novel game research platform expands the frontiers of automatic game balancing problems and offers a framework within a realistic game production pipeline., Comment: 14 pages, 6 figures, 6 tables, 2 algorithms

Ad-hoc team cooperation is the problem of cooperating with other players that have not been seen in the learning process. Recently, this problem has been considered in the context of Hanabi, which requires cooperation without explicit communication with the other players. While in self-play strategies cooperating on reinforcement learning (RL) process has shown success, there is the problem of failing to cooperate with other unseen agents after the initial learning is completed. In this paper, we categorize the results of ad-hoc team cooperation into Failure, Success, and Synergy and analyze the associated failures. First, we confirm that agents learning via RL converge to one strategy each, but not necessarily the same strategy and that these agents can deploy different strategies even though they utilize the same hyperparameters. Second, we confirm that the larger the behavioral difference, the more pronounced the failure of ad-hoc team cooperation, as demonstrated using hierarchical clustering and Pearson correlation. We confirm that such agents are grouped into distinctly different groups through hierarchical clustering, such that the correlation between behavioral differences and ad-hoc team performance is -0.978. Our results improve understanding of key factors to form successful ad-hoc team cooperation in multi-player games., Comment: 8 pages, 7 figures

In this paper, we investigate the fundamentals of puncturing and shortening for polar codes, based on binary domination which plays a key role in polar code construction. We first prove that the orders of encoder input bits to be made incapable (by puncturing) or to be shortened are governed by binary domination. In particular, we show that binary domination completely determines incapable or shortened bit patterns for polar codes, and that all the possible incapable or shortened bit patterns can be identified. We then present the patterns of the corresponding encoder output bits to be punctured or fixed, when the incapable or shortened bits are given. We also demonstrate that the order and the pattern of puncturing and shortening for polar codes can be aligned. In the previous work on the rate matching for polar codes, puncturing of encoder output bits begins from a low-indexed bit, while shortening starts from a high-indexed bit. Unlike such a conventional approach, we show that encoder output bits can be punctured from high-indexed bits, while keeping the incapable bit pattern exactly the same. This makes it possible to design a unified circular-buffer rate matching (CB-RM) scheme that includes puncturing, shortening, and repetition.

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., Comment: IEEE Transactions on Games

Hair cells conduct auditory transduction in vertebrates. In lower vertebrates such as frogs and turtles, due to the active mechanism in hair cells, hair bundles(stereocilia) can be spontaneously oscillating or quiescent. Recently, the amplitude death phenomenon has been proposed [K.-H. Ahn, J. R. Soc. Interface, {\bf 10}, 20130525 (2013)] as a mechanism for auditory transduction in frog hair-cell bundles, where sudden cessation of the oscillations arises due to the coupling between non-identical hair bundles. The gating of the ion channel is intrinsically stochastic due to the stochastic nature of the configuration change of the channel. The strength of the noise due to the channel gating can be comparable to the thermal Brownian noise of hair bundles. Thus, we perform stochastic simulations of the elastically coupled hair bundles. In spite of stray noisy fluctuations due to its stochastic dynamics, our simulation shows the transition from collective oscillation to amplitude death as inter-bundle coupling strength increases. In its stochastic dynamics, the formation of the amplitude death state of coupled hair bundles can be seen as a sudden suppression of the displacement fluctuation of the hair bundles as the coupling strength increases. The enhancement of the signal-to-noise ratio through the amplitude death phenomenon is clearly seen in the stochastic dynamics. Our numerical results demonstrate that the multiple number of transduction channels per hair bundle is an important factor to the amplitude death phenomenon, because the phenomenon may disappear for a small number of transduction channels due to strong gating noise., Comment: accepted in Physical Review E

We investigate electric and magnetic properties of graphene with rotationally symmetric strain. The strain generates large pseudo magnetic field with alternating sign in space, which forms a strongly confined quantum dot connected to six chiral channels. The orbital magnetism, degeneracy, and channel opening can be understood from the interplay between real and pseudo magnetic field which have different parities under time reversal and mirror reflection. While the orbital magnetic response of the confined state is diamagnetic, it can be paramagnetic if there is an accidental degeneracy with opposite mirror reflection parity.