Evolving Behaviour Trees for the Commercial Game DEFCON

Lim, Chong-U; Baumgarten, Robin; Colton, Simon

doi:10.1007/978-3-642-12239-2_11

Cited by 103 publications

(75 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Behavior trees have also become popular in the game development industry [10]. Primarily they have been used as an alternative to existing game AI systems, which were previously implemented by finite state machines (FSMs) and in particular HSMs [11].…”

Section: A the Behaviors Architecture For Robotic Tasks (Bart)mentioning

confidence: 99%

An integrated system for autonomous robotics manipulation

Bagnell

Cavalcanti

Cui

et al. 2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

102

View full text Add to dashboard Cite

Abstract-We describe the software components of a robotics system designed to autonomously grasp objects and perform dexterous manipulation tasks with only high-level supervision. The system is centered on the tight integration of several core functionalities, including perception, planning and control, with the logical structuring of tasks driven by a Behavior Tree architecture. The advantage of the implementation is to reduce the execution time while integrating advanced algorithms for autonomous manipulation. We describe our approach to 3-D perception, real-time planning, force compliant motions, and audio processing. Performance results for object grasping and complex manipulation tasks of in-house tests and of an independent evaluation team are presented.

show abstract

Section: A the Behaviors Architecture For Robotic Tasks (Bart)mentioning

confidence: 99%

An integrated system for autonomous robotics manipulation

Bagnell

Cavalcanti

Cui

et al. 2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

102

View full text Add to dashboard Cite

show abstract

“…There is currently, however, little research into automated manipulation or improvement of an initial BT implementation. Lim, Baumgarten and Colton [27] made use of evolutionary algorithms. They generated BTs by creating an initial population of trees and used genetic operators to produce improved BTs in the computer game DEFCON.…”

Section: B Machine Learning and Btsmentioning

confidence: 99%

QL-BT: Enhancing behaviour tree design and implementation with Q-learning

Dey

Child

2013

2013 IEEE Conference on Computational Inteligence in Games (CIG)

View full text Add to dashboard Cite

This is the unspecified version of the paper.This version of the publication may differ from the final published version. Abstract-Artificial intelligence has become an increasingly important aspect of computer game technology, as designers attempt to deliver engaging experiences for players by creating characters with behavioural realism to match advances in graphics and physics. Recently, behaviour trees have come to the forefront of games AI technology, providing a more intuitive approach than previous techniques such as hierarchical state machines, which often required complex data structures producing poorly structured code when scaled up. The design and creation of behaviour trees, however, requires experience and effort. This research introduces Q-learning behaviour trees (QL-BT), a method for the application of reinforcement learning to behaviour tree design. The technique facilitates AI designers' use of behaviour trees by assisting them in identifying the most appropriate moment to execute each branch of AI logic, as well as providing an implementation that can be used to debug, analyse and optimize early behaviour tree prototypes. Initial experiments demonstrate that behaviour trees produced by the QL-BT algorithm effectively integrate RL, automate tree design, and are human-readable. Permanent repository link

show abstract

“…The work of Lim et al [14] specifically dealt with evolving behaviour tree structures. It used GP to evolve AI controllers for the DEFCON game; the final evolved tree was pitted against the standard DEFCON AI controller, and achieved a success rate superior to 50%.…”

Section: Relevant Literaturementioning

confidence: 99%

“…In the previous example, Mario would be in the coordinates (225/16, 53/16) = (14,3), and the brick block in (14 + 1, 3 − 2) = (15, 1).…”

Section: Path Planning With A*mentioning

confidence: 99%

“…The BT (XML) syntax was specified in the grammar, and all conditions (18), actions (15), sub-trees (14) and filters (4) were available. In the first version of this work [24], it was shown that restricting the structure of BTs was necessary, in order to avoid the evolution of syntactically correct but semantically non-sensical BTs; this was achieved with a carefully designed grammar.…”

Section: Using Ge To Evolve Btsmentioning

confidence: 99%

See 1 more Smart Citation

Reactiveness and navigation in computer games: Different needs, different approaches

Pérez

Nicolau

O’Neill

et al. 2011

2011 IEEE Conference on Computational Intelligence and Games (CIG'11)

View full text Add to dashboard Cite

o u l , S o u t h K o r e a , A u g u s t 3 1 s t -S e p t e m b e r 3 r d 2 0 1 1 Abstract This paper presents an approach to the Mario AI Benchmark problem, using the A* algorithm for navigation, and an evolutionary process combining routines for the reactiveness of the resulting bot. The Grammatical Evolution system was used to evolve Behaviour Trees, combining both types of routines, while the highly dynamic nature of the environment required specific approaches to deal with overfitting issues. The results obtained highlight the need for specific algorithms for the different aspects of controlling a bot in a game environment, while Behaviour Trees provided the perfect representation to combine all those algorithms.

show abstract

Evolving Behaviour Trees for the Commercial Game DEFCON

Cited by 103 publications

References 7 publications

An integrated system for autonomous robotics manipulation

An integrated system for autonomous robotics manipulation

QL-BT: Enhancing behaviour tree design and implementation with Q-learning

Reactiveness and navigation in computer games: Different needs, different approaches

Contact Info

Product

Resources

About