言語誘導型特徴変換モジュールGFT:身体性エージェントのための言語接地
Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
生の画素・言語コマンド・疎な報酬から端到端で学習できる言語接地モジュールを提案し、文埋め込みを変換行列として視覚特徴を言語誘導で変換することで、言語指示ナビゲーションタスクで最先端を上回った。
著者: Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu
分類: cs.AI, cs.CL, cs.LG, cs.RO
原文アブストラクト
Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding module for embodied agents that can be trained end to end from scratch taking raw pixels, unstructured linguistic commands, and sparse rewards as the inputs. We model the language grounding process as a language-guided transformation of visual features, where latent sentence embeddings are used as the transformation matrices. In several language-directed navigation tasks that feature challenging partial observability and require simple reasoning, our module significantly outperforms the state of the art. We also release XWorld3D, an easy-to-customize 3D environment that can potentially be modified to evaluate a variety of embodied agents.
