• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.3
• /
• pp.170-177
• /
• 2010

Poker is a game of imperfect information where competing players must deal with multiple risk factors stemming from unknown information while making the best decision to win, and this makes it an interesting test-bed for artificial intelligence research. This paper introduces a new learning AI algorithm with embedded opponent modeling that can be used for these types of situations and we use this AI and apply it to a poker program. The new AI will be based on several graphs with each of its nodes representing inputs, and the algorithm will learn the optimal decision to make by updating the weight of the edges connecting these nodes and returning a probability for each action the graphs represent.

• Journal of KIISE:Software and Applications
• /
• v.35 no.3
• /
• pp.179-188
• /
• 2008

An important issue in multiagent reinforcement learning is how an agent should team its optimal policy through trial-and-error interactions in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for multiagent reinforcement teaming tend to apply single-agent reinforcement learning techniques without any extensions or are based upon some unrealistic assumptions even though they build and use explicit models of other agents. In this paper, basic concepts that constitute the common foundation of multiagent reinforcement learning techniques are first formulated, and then, based on these concepts, previous works are compared in terms of characteristics and limitations. After that, a policy model of the opponent agent and a new multiagent reinforcement learning method using this model are introduced. Unlike previous works, the proposed multiagent reinforcement learning method utilize a policy model instead of the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper. the Cat and Mouse game is introduced as an adversarial multiagent environment. And effectiveness of the proposed multiagent reinforcement learning method is analyzed through experiments using this game as testbed.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.1
• /
• pp.83-90
• /
• 2008

Taekwondo is a martial art form and sport that uses the hands and foot for attack and defense. Taekwondo basic motion is composed of the breaking, competition and poomsea motion. In the side kick among the competition motion, the impact force is larger than other kinds of kicks. The side kick with the front foot can be made in two steps. In the first step, the front foot is stretched forward from back stance free-fighting position. For the second step, the rear foot is followed simultaneously. Then, the kick is executed while entire body weight rests on the rear foot. In this paper, impact analysis of the human model for hitting posture is carried out. The ADAMS/LifeMOD is used in hitting modeling and simulation. The simulation model creates the human model to hit the opponent. As the results, the dynamic analysis of human muscle were presented.

• Management Science and Financial Engineering
• /
• v.19 no.2
• /
• pp.31-36
• /
• 2013

We propose a war-game model that is appropriate for a raid-type warfare in which, a priori, the maneuver of the attacker is relatively certain. The model is based on a multi-weapon extention of the Lanchester's law. Instead of a continuous time dynamic game with the differential equations from the Lanchester's law, however, we adopt a multi-period model relying on a time-discretization of the Lanchester's law. Despite the obvious limitation that two players make a move only on the discrete time epochs, the pragmatic model has a manifold justification. The existence of an equilibrium is readily established by its equivalence to a finite zero-sum game, the existence of whose equilibrium is, in turn, well-known to be no other than the LP-duality. It implies then that the war-game model dictates optimal strategies for both players under the assumption that any strategy choice of each player will be responded by a best strategy of her opponent. The model, therefore, provides a sound ground for finding an efficient reinforcement of a defense system that guarantees peaceful equilibria.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.39-46
• /
• 2020

The utilization of artificial intelligence (AI) in the engagement has been a key research topic in the defense field during the last decade. To pursue this utilization, it is imperative to acquire a realistic simulation to train an AI engagement agent with a synthetic, but realistic field. This paper is a case study of training an AI agent to operate with a hardware realism in the air-warfare dog-fighting. Particularly, this paper models the pursuit of an opponent in the dog-fighting setting with a gun-only engagement. In this context, the AI agent requires to make a decision on the pursuit style and intensity. We developed a realistic hardware simulator and trained the agent with a reinforcement learning. Our training shows a success resulting in a lead pursuit with a decreased engagement time and a high reward.