This paper introduces a novel path planning technique called MCRT which is aimed at non-deterministic, partially known, real-time domains populated with dynamically moving obstacles, such as might be found in a real-time strategy (RTS) game. The technique combines an efficient form of Monte-Carlo tree search with the randomized exploration capabilities of rapidly exploring random tree (RRT) planning. The main innovation of MCRT is in incrementally building an RRT structure with a collision-sensitive reward function, and then re-using it to efficiently solve multiple, sequential goals. We have implemented the technique in MCRT-planner, a program which solves non-deterministic path planning problems in imperfect information RTS games, and evaluated it in comparison to four other state of the art techniques. Planners embedding each technique were applied to a typical RTS game and evaluated using the game score and the planning cost. The empirical evidence demonstrates the success of MCRT-planner.

No abstract

In this paper, coevolution is used to evolve square board. The start position of the game is shown in Artificial Neural Networks (ANN) which evaluate board Figure 1. The player who always starts the game is the Black positions of a two player zero-sum game (The Virus Game). The Player and the other player is the White Player. coevolved neural networks play at a level that beats a group of In the Virus Game, there are two kinds of moves available strong hand-crafted Al players. We investigate the performance of coevolution starting from random initial weights and starting for e . this kind of move i groe move or on with weights that are tuned by gradient based adaptive learning step move. In this kind of move, a player moves a piece of methods (Backpropagation, RPROP and iRPROP). The results his colour to an empty position adjacent to its current of coevolutionary experiments show that pre training of the position. The positions are adjacent if their borders or population is highly effective in this case.corners are adjacent. The result of this move reproduces the moving piece and occupies both positions, the new position

No abstract

Malware detection is a challenging and non-trivial task due to ever increase in several attacks and their sophistication level. Detection of such attacks demands the exploration of new approaches to generalize the attack patterns. One such approach is the use of Monte-Carlo simulations to train a reinforcement learning model. In this paper, we propose a self-adaptive Monte-Carlo simulation-based reinforcement model called Heuristic-based Generative Model (HGM), which generalizes the attack patterns in such a way that the new unknown attacks can be detected and flagged in real-time. The results show that HGM can detect a variety of malware with high accuracy.

The use of innovative and sophisticated malware definitions poses a serious threat to computer-based information systems. Such malware is adaptive to the existing security solutions and often works without detection. Once malware completes its malicious activity, it self-destructs and leaves no obvious signature for detection and forensic purposes. The detection of such sophisticated malware is very challenging and a non-trivial task because of the malware’s new patterns of exploiting vulnerabilities. Any security solutions require an equal level of sophistication to counter such attacks. In this paper, a novel reinforcement model based on Monte-Carlo simulation called eRBCM is explored to develop a security solution that can detect new and sophisticated network malware definitions. The new model is trained on several kinds of malware and can generalize the malware detection functionality. The model is evaluated using a benchmark set of malware. The results prove that eRBCM can identify a variety of malware with immense accuracy.

No abstract

No abstract