• The Journal of Information Systems
• /
• v.25 no.4
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.

• Journal of Korea Game Society
• /
• v.17 no.3
• /
• pp.63-70
• /
• 2017

In AI research Go is regarded as the most challenging board game due to the positional evaluation difficulty and the huge branching factor. MCTS is an exciting breakthrough to overcome these problems. The idea behind AlphaGo was to estimate the winning rate of a given position and then to lead deeper search for finding the best promising move. In this paper, using non-strategic MCTS we verified the fact that most pro players regard the best first move as Tengen (Origin of heaven) in $9{\times}9$ Go is correct. We also compared the average winning rates of the most popular first moves.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.1-6
• /
• 2021

Most of the match-3 puzzle games supports automatic play using the MCTS algorithm. However, implementing reinforcement learning agents is not an easy job because it requires both the knowledge of machine learning and the way of complex interactions within the development environment. This study proposes a method in which we can easily design reinforcement learning agents and implement game play agents by applying PPO(Proximal Policy Optimization) algorithms. And we could identify the performance was increased about 44% than the conventional method. The tools we used are the Unity 3D game engine and Unity ML SDK. The experimental result shows that agents became to learn game rules and make better strategic decisions as experiments go on. On average, the puzzle gameplay agents implemented in this study played puzzle games better than normal people. It is expected that the designed agent could be used to speed up the game level design process.