n Yin Chu

Deduction of fighting-game countermeasures using the k-nearest neighbor algorithm and a game simulator

This paper proposes an artificial intelligence algorithm that uses the k-nearest neighbor algorithm to predict its opponents attack action and a game simulator to deduce a countermeasure action for controlling an in-game character in a fighting game. This AI algorithm (AI) aims at achieving good results in the fighting-game AI competition having been organized by our laboratory since 2013. It is also a sample AI, called MizunoAI, publicly available for the 2014 competition at CIG 2014. In fighting games, every action is either advantageous or disadvantageous against another. By predicting its opponents next action, our AI can devise a countermeasure which is advantageous against that action, leading to higher scores in the game. The effectiveness of the proposed AI is confirmed by the results of matches against the top-three AI entries of the 2013 competition.

Combining pathfmding algorithm with Knowledge-based Monte-Carlo tree search in general video game playing

This paper proposes a general video game playing AI that combines a pathfmding algorithm with Knowledge-based Fast-Evolutionary Monte-Carlo tree search (KB Fast-Evo MCTS). This AI is able to acquire knowledge of the game through simulation, select suitable targets on the map using the acquired knowledge, and head to the target in an efficient manner. In addition, improvements have been proposed to handle various features of the GVG-AI platform, including avatar type changes, portals and item usage. Experiments on the GVG-AI Competition framework has shown that our proposed AI can adapt to a wide range of video games, and performs better than the original KB Fast-Evo MCTS controller in 75% of all games tested, with a 64.2% improvement on the percentage of winning.

Applying and Improving Monte-Carlo Tree Search in a Fighting Game AI

This paper evaluates the performance of Monte-Carlo Tree Search (MCTS) in a fighting game AI and proposes an improvement for the algorithm. Most existing fighting game AIs rely on rule bases and react to every situation with predefined actions, making them predictable for human players. We attempt to overcome this weakness by applying MCTS, which can adapt to different circumstances without relying on predefined action patterns or tactics. In this paper, an AI based on Upper Confidence bounds applied to Trees (UCT) and MCTS is first developed. Next, the paper proposes improving the AI with Roulette Selection and a rule base. Through testing and evaluation using FightingICE, an international fighting game AI competition platform, it is proven that the aforementioned MCTS-based AI is effective in a fighting game, and our proposed improvement can further enhance its performance.

Position-based reinforcement learning biased MCTS for General Video Game Playing

This paper proposes an application of reinforcement learning and position-based features in rollout bias training of Monte-Carlo Tree Search (MCTS) for General Video Game Playing (GVGP). As an improvement on Knowledge-based Fast-Evo MCTS proposed by Perez et al., the proposed method is designated for both the GVG-AI Competition and improvement of the learning mechanism of the original method. The performance of the proposed method is evaluated empirically, using all games from six training sets available in the GVG-AI Framework, and the proposed method achieves better scores than five other existing MCTS-based methods overall.

Procedural generation of angry birds levels that adapt to the player's skills using genetic algorithm

This paper proposes a procedural generation method that automatically creates game levels for Angry Birds, a famous mobile game, using genetic algorithm. By adjusting the parameters of the genetic algorithm according to the players gameplay results, our proposed method can generate game levels that adapt to the players skills. Our experiment proves that the proposed method is able to procedurally generate game levels that befit the players skill.

Efficient implementation of breadth first search for general video game playing

This paper proposes an efficient implementation of Breadth First Search (BFS) for General Video Game Playing (GVGP). This method is specialized for deterministic games, which often cannot be solved by a single action and require a more extensive search to solve. Most existing AI programs cannot search the game space efficiently, and thus perform poorly in deterministic games. To improve the efficiency of tree search, we propose limiting the branching of game tree in BFS. Hash code is assigned to each tree node and used to identify similar game states. A tree node with a game state that has been visited in previous search will not be expanded. Using a deterministic game set for evaluation, our experiment shows that the proposed method outperforms existing methods.