Behavior hierarchy learning in a behavior-based system using reinforcement learning

Amir Massoud Farahmand, Majid Nili Ahmadabadi, Babak Nadjar AraabiIROS 2004 · OpenReview

Abstract

Hand-design of an intelligent agent's behaviors and their hierarchy is a very hard task. One of the most important steps toward creating intelligent agents is providing them with capability to learn the required behaviors and their architecture. Architecture learning in a behavior-based agent with subsumption architecture is considered in this paper. Overall value function is decomposed into easily calculate-able parts in order to learn the behavior hierarchy. Using probabilistic formulations, two different decomposition methods are discussed: storing the estimated value of each behavior in each layer, and storing the ordering of behaviors in the architecture. Using defined decompositions, two appropriate credit assignment methods are designed. Finally, the proposed methods are tested in a multi-robot object-lifting task that results in satisfactory performance.
BibTeX
@inproceedings{farahmand2004behavior,
  author = {Amir Massoud Farahmand and Majid Nili Ahmadabadi and Babak Nadjar Araabi},
  title = {{Behavior hierarchy learning in a behavior-based system using reinforcement learning}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2004},
  url = {https://openreview.net/forum?id=ZhnFGwB0Ofq},
}

Loading related content...

Figure