Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree

  title={Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree},
  author={Clemente Rubio-Manzano and Tom{\'a}s Lermanda Senocea{\'i}n and Claudia Martinez-Araneda and Alejandra Andrea Segura Navarrete and Christian Vidal-Castro},
In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception network based on the execution traces of the games and, second, representing it using fuzzy logic (linguistic variables and if-then rules). From this knowledge, a set of data (dataset) is automatically created to generate a learning model based on decision… 

Figures and Tables from this paper



Learning Human-Like Movement Behavior for Computer Games

This work proposes an approach for learning strategies by observation of human players, principally viewing the design of a computer game agent as a problem of pattern recognition.

Improving player experience in Computer Games by using players' behavior analysis and linguistic descriptions

Bayesian imitation learning in game characters

This paper will present experiments in imitation learning from the network traffic of multi-player online games, and underline that this produces agents that behave more human-like than characters controlled by common game AI techniques.

Imitative learning for real-time strategy games

This paper proposes a generic method allowing real-time strategy (RTS) agents to learn production strategies from a set of recorded games using supervised learning and successfully teaches a Terran agent facing a Protoss opponent new production strategies.

Imitation learning at all levels of game-AI

If and how the principle of imitation learning can facilitate the programing of life-like computer game charecters and different algorithms that learn from human generated training data are presented and it is shown that machine learning can be applied on different levels of cognitive abstraction.

Towards Interactive Training of Non-Player Characters in Video Games

This work proposes to create such NPC behaviors interactively by training an agent in the target environment using imitation learning with a human in the loop, and shows that interactivity can substantially improve it with a modest amount of human efforts.

Behavior Trees for Modelling Artificial Intelligence in Games: A Tutorial

This tutorial introduction to behavior trees is provided, which are a useful way of structuring artificial intelligence in games and recommend that behavior trees be used when some game designers are not programmers, the conditions governing the behavior are complex, and the NPCs have aspects of behavior in common.

Automated Derivation of Primitives for Movement Classification

A method for automatically deriving a set of primitives directly from human movement data, using movement data gathered from a psychophysical experiment on human imitation to derive the primitives.

Learning Hierarchical Performance Knowledge by Observation

The knowledge required for task performance is described, how this knowledge is learned is described by KnoMic, and efforts to learn performance knowledge in the tactical air combat domain and the computer game Quake II are reported on.