Finding Comfortable Settings of Snake Game Using Game Refinement Measurement

Punyawee, Anunpattana; Panumate, Chetprayoon; Iida, Hiroyuki

doi:10.1007/978-981-10-3023-9_11

Cited by 9 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that we assume the estimation of the plausible candidates as described in Eq. (8). From Figure 3 we conjecture that the parameter c relates Remark 3.…”

Section: Possible Interpretations For Game Refinement Measurementioning

confidence: 85%

See 1 more Smart Citation

Possible Interpretations for Game Refinement Measure

Xiong

Zuo

Iida

2017

Entertainment Computing – ICEC 2017

Self Cite

View full text Add to dashboard Cite

This paper explores possible interpretations for game refinement measure which has been successfully used to quantify the game sophistication of various types of games such as boardgames and sports. It presents a brief sketch of game refinement theory with a focus on its early works with boardgames, expansion into continuous movement games such as sports, and a bridge between sports and boardgames. It then highlights the bridging idea while considering possible interpretations for game refinement measure, and the meaning of game refinement measure is discussed with a focus on the skill and chance aspects in game playing. It enables to have a new perspective of game refinement theory. Moreover, an example of interpretation for game refinement measure from boardgames and continuous movement games such as MOBA game is shown. The interpretation is well fitting to our intuition as game players and spectators.

show abstract

“…Note that we assume the estimation of the plausible candidates as described in Eq. (8). From Figure 3 we conjecture that the parameter c relates Remark 3.…”

Section: Possible Interpretations For Game Refinement Measurementioning

confidence: 85%

“…In particular, game refinement theory gives a measure to quantify the sophistication of a game. This enables to obtain the deep insight into the current game and improve the quality of the game [7,8].…”

Section: Introductionmentioning

confidence: 99%

Possible Interpretations for Game Refinement Measure

Xiong

Zuo

Iida

2017

Entertainment Computing – ICEC 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Determining the match between the considered game progress model and game information is an essential and challenging task. The current game progress model is mainly used for board or tabletop games [25,31,32], time-limited games [33][34][35], scorelimited games [28,33,35], and video games [36,37]. For a board game, a move selection model was adopted, where an efficient algorithm (such as αβ algorithm) or players with sufficient ability (such as Grandmaster), was/were able to derive a few plausible options (b) from all possible options (i.e., branching factors of a tree-search, B).…”

Section: Original Game Progress Modelmentioning

confidence: 99%

MMORPG Evolution Analysis from Explorer and Achiever Perspectives: A Case Study Using the Final Fantasy Series

et al. 2021

Self Cite

View full text Add to dashboard Cite

Due to the advent of the Internet, massively multiplayer online role-playing games (MMORPGs) have been enjoyed worldwide by many players simultaneously, and game publishers’ revenues have reached billions of dollars from subscriptions alone. Frequent updates (e.g., versioning) and new contents (e.g., quest system) are the typical strategies adopted by developers to keep MMORPG experiences fresh and attractive. What makes such strategies attractive and retains the interest of players in MMORPGs? This study focuses on one aspect of a popular MMORPG: the player’s experience of the quest systems of Final Fantasy XIV (FF14). The different quest systems were analyzed considering Bartle’s players’ classification, specifically for the explorers and achievers. From an information science perspective, such an analysis can be achieved via game refinement (GR) theory, which formulates the information of the game’s progression into a measurable model of game sophistication. On top of that, we used the concept of motion in mind, which was derived from concepts in physics. It maps game progression information to enable the possible quantification and approximation of players’ mental movements and affective experiences in the game. Based on the analysis of the collected data using the proposed measures of GR and motion in mind, the impact of regular updates on players in long-term games is discussed. Insights from the study provide guidance and suggestions for potential improvements in long-term game design.

show abstract

“…In this work, we implemented the Snake Game in Python as the testbed of autonomous agents. We adopted the settings of the Snake Game as recommended by [8]. Specifically, the size of the game map is set to 240×240 in pixel and divided into 12×12 equally large grids.…”

Section: A Game Environmentmentioning

confidence: 99%

Autonomous Agents in Snake Game via Deep Reinforcement Learning

Wei

Wang

Zhang

et al. 2018

2018 IEEE International Conference on Agents (ICA)

View full text Add to dashboard Cite

Since DeepMind pioneered a deep reinforcement learning (DRL) model to play the Atari games, DRL has become a commonly adopted method to enable the agents to learn complex control policies in various video games. However, similar approaches may still need to be improved when applied to more challenging scenarios, where reward signals are sparse and delayed. In this paper, we develop a refined DRL model to enable our autonomous agent to play the classical Snake Game, whose constraint gets stricter as the game progresses. Specifically, we employ a convolutional neural network (CNN) trained with a variant of Q-learning. Moreover, we propose a carefully designed reward mechanism to properly train the network, adopt a training gap strategy to temporarily bypass training after the location of the target changes, and introduce a dual experience replay method to categorize different experiences for better training efficacy. The experimental results show that our agent outperforms the baseline model and surpasses humanlevel performance in terms of playing the Snake Game.

show abstract

Finding Comfortable Settings of Snake Game Using Game Refinement Measurement

Cited by 9 publications

References 7 publications

Possible Interpretations for Game Refinement Measure

Possible Interpretations for Game Refinement Measure

MMORPG Evolution Analysis from Explorer and Achiever Perspectives: A Case Study Using the Final Fantasy Series

Autonomous Agents in Snake Game via Deep Reinforcement Learning

Contact Info

Product

Resources

About