Self-organizing neural networks for learning air combat maneuvers

Learning Behavior Trees for Autonomous Agents with Hybrid Constraints Evolution

“…On the other side of the spectrum, various approaches are emerged in machine learning community to generate adaptive agent behavior automatically [5,[20][21][22]. This field has been studied basically from two perspectives [1,2]: learning from observation (LfO) (a.k.a, learning from demonstration, programming from demonstration) and learning from experience.…”

“…Ontañón et al [23] use learning from demonstration for realtime strategy games in the context of case-based planning. While the later leads virtual agent to learn and optimize its behavior by interacting with environment repeatedly (e.g., reinforcement learning and evolutionary algorithms) [5,22]. The performance of the agent is measured according to how well the task is performed as expert's evaluation criterions, which may sometimes find creative solutions that are not found by humans termed as computational creativity [4].…”

“…For instance, Aihe and Gonzalez [24], propose Reinforcement learning (RL) to compensate for situations where the domain expert has limited knowledge of the subject being modeled. Teng et al [22] use a self-organizing neural network to learn incrementally through real-time interactions with the environment, which can improve air combat maneuvering strategies of CGFs. Please note that most of those machine learning methods generate behavior model as a black box system [6,7].…”

Study on Consulting Air Combat Simulation of Cluster UAV Based on Mixed Parallel Computing Framework of Graphics Processing Unit

“…However, due to the computational overload caused by the curse of dimensionality, the traditional RL method is not suitable for solving large-scale Markov decision processes (MDP) such as air combat. In [12,13], an approximate learning method combining approximation techniques with reinforcement learning is used to approximate a value function or a state space by a function approximator. Avoiding accurate solutions can alleviate the problems caused by the dimensional curse to a certain extent.…”

Computational techniques for modeling non-player characters in games

“…Recently, the modeling of N-PCs has been intensively studied all over the world, along with the development of computer technologies. The NPCs technologies could be commonly applied in extensive areas such as commercial games, the virtual spaces with education or nursing purposes [63] [165], and computer generated forces (CGF) in military command and control simulations [113] [155] [154]. In these areas, NPCs are required to realize artificial and humanoid performance such as behavior ability, affective expression ability, learning ability and adaptability.…”