[PDF] QL-BT: Enhancing behaviour tree design and implementation with Q-learning | Semantic Scholar (2024)

Figures and Tables from this paper

  • figure 1
  • table 1
  • figure 2
  • figure 3
  • figure 4
  • figure 6

Topics

Behaviour Trees (opens in a new tab)Reinforcement Learning (opens in a new tab)Behavioral Realism (opens in a new tab)Graphics (opens in a new tab)Artificial Intelligence (opens in a new tab)Q-learning (opens in a new tab)

49 Citations

Trained Behavior Trees: Programming by Demonstration to Support AI Game Designers
    Ismael Sagredo-OlivenzaP. P. Gómez-MartínM. A. Gómez-MartínP. González-Calero

    Computer Science

    IEEE Transactions on Games

  • 2019

TBTs are behavior trees (BTs) generated from traces obtained in a game through PbD that facilitate the use of BTs by game designers and promote their authoring control on game AI.

  • 32
Learning Behavior Trees for Autonomous Agents with Hybrid Constraints Evolution
    Qi ZhangJian YaoQuanjun YinYabing Zha

    Computer Science

    Applied Sciences

  • 2018

A novel idea of dynamic constraint based on frequent sub-trees mining, which can accelerate evolution by protecting preponderant behavior sub-Trees from undesired crossover, is proposed and introduced into the evolving BTs with hybrid constraints (EBT-HC).

Interpretable Reinforcement Learning of Behavior Trees
    Chenjing ZhaoChuanshuai Deng Xiaodong Yi

    Computer Science

    ICMLC

  • 2023

This paper presents intelligent generation methods that directly represent the policies generated by Q-learning and its derived algorithms in the form of BTs to enhance the interpretability of RL.

  • 1
Integrating Reinforcement Learning into Behavior Trees by Hierarchical Composition
    Mart KartasevAron Granberg

    Computer Science, Art

  • 2019

This thesis investigates ways to extend the use of Reinforcement Learning (RL) to Behavior Trees (BTs) by using existing general-purpose RL methods within the framework of BTs.

Mixed Deep Reinforcement Learning-behavior Tree for Intelligent Agents Design
    Lei LiLei WangYuanzhi LiJ. Sheng

    Computer Science, Engineering

    ICAART

  • 2021

This work investigates a general and extendable model of mixed behavior tree (MDRL-BT) upon the option framework where the hierarchical architecture simultaneously involves different deep reinforcement learning nodes and normal BT nodes.

  • 5
  • PDF
Agents that learn to behave with reinforcement learning and behavior trees
    Rafael MarquesMarçal de Sousa

    Computer Science

  • 2021

A novel decanonicalization algorithm that converts a policy obtained from RL into a human legible Behavior Tree (BT), an architecture praised for its modularity and reactivity that can assist designers in testing and debugging and allow the users to better predict its behavior, thus cutting on development time and costs.

  • PDF
Behavior Modeling for Autonomous Agents Based on Modified Evolving Behavior Trees
    Qi ZhangKai XuPeng JiaoQuanjun Yin

    Computer Science

    2018 IEEE 7th Data Driven Control and Learning…

  • 2018

Preliminary experiments show that the proposed modified evolving behavior trees approach to model agent behavior as a BT outperforms standard evolving behavior tree by achieving better final behavior performance with less learning episodes.

  • 7
Combining behavior trees with MAXQ learning to facilitate CGFs behavior modeling
    Qi ZhangLin SunPeng JiaoQuanjun Yin

    Computer Science

    2017 4th International Conference on Systems and…

  • 2017

Preliminary experiments in a predator-prey simulation scenario show that MAXQ-BT can facilitate behavior trees generation easily for CGF to achieve better behavior performance than handcrafted products.

  • 11
  • Highly Influenced
Improving the Performance of Backward Chained Behavior Trees that use Reinforcement Learning
    Mart KartasevJustin SalerPetter Ögren

    Computer Science

    2023 IEEE/RSJ International Conference on…

  • 2023

This paper proposes a way to set up the RL problems, such that they do not only achieve each immediate subgoal, but also avoid violating the identified ACCs.

Improving the Performance of Backward Chained Behavior Trees using Reinforcement Learning
    Mart KartasevJustin SalerPetter Ögren

    Computer Science

    ArXiv

  • 2021

The key idea of this letter is to improve performance of backward chained BTs by using the conditions identified in the theoretical convergence proof to setup RL problems for individual controllers to avoid violating the identified ACCs.

  • 1

...

...

27 References

Dynamic Expansion of Behaviour Trees
    G. PugaM. A. Gómez-MartínBelén Díaz-AgudoP. González-Calero

    Computer Science

    AIIDE

  • 2008

This paper focuses on dynamic retrieval of behaviours taking into account the world state and the underlying goals to select the most appropriate state machine to guide the NPC behaviour.

  • 28
  • PDF
Applying hierarchical reinforcement learning to computer games
    Du XiaoqinL. QinghuaHan Jianjun

    Computer Science

    2009 IEEE International Conference on Automation…

  • 2009

The result shows that this method can satisfy the need for controlling NPC and has faster convergence speed than flat reinforcement learning.

  • 6
Evolving Behaviour Trees for the Commercial Game DEFCON
    Chong-U LimRobin BaumgartenS. Colton

    Computer Science

    EvoApplications

  • 2010

The use of behaviour trees are used to design and develop an AI-controlled player for the commercial real-time strategy game DEFCON which was able to outperform the game’s original AI-bot more than 50% of the time.

  • 143
  • PDF
Learning and evolving combat game controllers
    Luis PeñaSascha OssowskiJ. SánchezS. Lucas

    Computer Science

    2012 IEEE Conference on Computational…

  • 2012

Two new variants of a hybrid algorithm, named WEREWoLF and WERESARSA, that combine evolutionary techniques with reinforcement learning are introduced that allow a group of different reinforcement learning controllers to be recombined in an iterative process that uses both evolution and learning.

  • 19
  • PDF
Self-Validated Behaviour Trees through Reflective Components
    David LlansóM. A. Gómez-MartínP. González-Calero

    Computer Science

    AIIDE

  • 2009

An architecture for building the AI of an NPC that extends the component-based approach, which represents the functionality of an entity as a collection of functionality-specific components, and is able to identify faulty behaviour trees at design time.

  • 7
  • PDF
Recent Advances in Hierarchical Reinforcement Learning
    A. BartoS. Mahadevan

    Computer Science

    Discret. Event Dyn. Syst.

  • 2003

This work reviews several approaches to temporal abstraction and hierarchical organization that machine learning researchers have recently developed and discusses extensions of these ideas to concurrent activities, multiagent coordination, and hierarchical memory for addressing partial observability.

  • 555
Recent Advances in Hierarchical Reinforcement Learning
    A. BartoS. Mahadevan

    Computer Science

    Discret. Event Dyn. Syst.

  • 2003

This work reviews several approaches to temporal abstraction and hierarchical organization that machine learning researchers have recently developed and discusses extensions of these ideas to concurrent activities, multiagent coordination, and hierarchical memory for addressing partial observability.

  • 1,246
  • PDF
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
    Thomas G. Dietterich

    Computer Science

    J. Artif. Intell. Res.

  • 2000

The paper presents an online model-free learning algorithm, MAXQ-Q, and proves that it converges with probability 1 to a kind of locally-optimal policy known as a recursively optimal policy, even in the presence of the five kinds of state abstraction.

  • 1,660
  • PDF
Evolving Behaviour Trees for the Mario AI Competition Using Grammatical Evolution
    Diego Perez LiebanaMiguel NicolauM. O’NeillA. Brabazon

    Computer Science

    EvoApplications

  • 2011

The results obtained reinforce the applicability of evolutionary programming systems to the development of artificial intelligence in games, and in dynamic systems in general, illustrating their viability as an alternative to more standard AI techniques.

  • 92
  • PDF
Reinforcement Learning with Soft State Aggregation
    Satinder SinghT. JaakkolaMichael I. Jordan

    Computer Science

    NIPS

  • 1994

This paper presents a function approximator based on a simple extension to state aggregation (a commonly used form of compact representation), namely soft state aggregation, a theory of convergence for RL with arbitrary, but fixed, softstate aggregation, and a novel intuitive understanding of the effect of state aggregation on online RL.

  • 385
  • PDF

...

...

Related Papers

Showing 1 through 3 of 0 Related Papers

    [PDF] QL-BT: Enhancing behaviour tree design and implementation with Q-learning | Semantic Scholar (2024)

    References

    Top Articles
    Latest Posts
    Recommended Articles
    Article information

    Author: Melvina Ondricka

    Last Updated:

    Views: 6281

    Rating: 4.8 / 5 (48 voted)

    Reviews: 95% of readers found this page helpful

    Author information

    Name: Melvina Ondricka

    Birthday: 2000-12-23

    Address: Suite 382 139 Shaniqua Locks, Paulaborough, UT 90498

    Phone: +636383657021

    Job: Dynamic Government Specialist

    Hobby: Kite flying, Watching movies, Knitting, Model building, Reading, Wood carving, Paintball

    Introduction: My name is Melvina Ondricka, I am a helpful, fancy, friendly, innocent, outstanding, courageous, thoughtful person who loves writing and wants to share my knowledge and understanding with you.