ノイジーエージェント：聴覚イベント予測による自己教師あり探索
Noisy Agents: Self-supervised Exploration by Predicting Auditory Events
音のイベントを予測する誤差を内的報酬として強化学習エージェントの探索を促し、物理環境で物体との接触行動が自然に生まれることを示した研究。
著者: Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba, Joshua B. Tenenbaum
分類: cs.CV, cs.AI, cs.LG, cs.RO, cs.SD, eess.AS
原文アブストラクト
Humans integrate multiple sensory modalities (e.g. visual and audio) to build a causal understanding of the physical world. In this work, we propose a novel type of intrinsic motivation for Reinforcement Learning (RL) that encourages the agent to understand the causal effect of its actions through auditory event prediction. First, we allow the agent to collect a small amount of acoustic data and use K-means to discover underlying auditory event clusters. We then train a neural network to predict the auditory events and use the prediction errors as intrinsic rewards to guide RL exploration. Experimental results on Atari games show that our new intrinsic motivation significantly outperforms several state-of-the-art baselines. We further visualize our noisy agents' behavior in a physics environment and demonstrate that our newly designed intrinsic reward leads to the emergence of physical interaction behaviors (e.g. contact with objects).
