制約付き適応型ビヘイビアエージェントのためのフレームワーク
A Framework for Constrained and Adaptive Behavior-Based Agents
ビヘイビアツリーに強化学習ノードを組み込み、制約のあるエージェントに学習能力を付与するフレームワークを提案し、階層型強化学習のOptionsとの関係や収束性、他ノードへの非干渉性を実証した。
著者: Renato de Pontes Pereira, Paulo Martins Engel
分類: cs.AI, cs.LG, cs.RO, cs.SY, eess.SY
原文アブストラクト
Behavior Trees are commonly used to model agents for robotics and games, where constrained behaviors must be designed by human experts in order to guarantee that these agents will execute a specific chain of actions given a specific set of perceptions. In such application areas, learning is a desirable feature to provide agents with the ability to adapt and improve interactions with humans and environment, but often discarded due to its unreliability. In this paper, we propose a framework that uses Reinforcement Learning nodes as part of Behavior Trees to address the problem of adding learning capabilities in constrained agents. We show how this framework relates to Options in Hierarchical Reinforcement Learning, ensuring convergence of nested learning nodes, and we empirically show that the learning nodes do not affect the execution of other nodes in the tree.
