ロボットの内省的自己理解:ニューロン活性から内部状態を学習する
Intrinsic Robotic Introspection: Learning Internal States From Neuron Activations
特徴抽出ネットワークの活性をVAEで再構成して内部状態を構築し、actor-criticの行動選択性能を向上させ、学習に必要なエピソード数を約1300削減した。
著者: Nikos Pitsillos, Ameya Pore, Bjorn Sand Jensen, Gerardo Aragon-Camarasa
分類: cs.RO, cs.AI
原文アブストラクト
We present an introspective framework inspired by the process of how humans perform introspection. Our working assumption is that neural network activations encode information, and building internal states from these activations can improve the performance of an actor-critic model. We perform experiments where we first train a Variational Autoencoder model to reconstruct the activations of a feature extraction network and use the latent space to improve the performance of an actor-critic when deciding which low-level robotic behaviour to execute. We show that internal states reduce the number of episodes needed by about 1300 episodes while training an actor-critic, denoting faster convergence to get a high success value while completing a robotic task.
