Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

Abstract

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.

arXiv commentCoRL 2018

References in corpus (13)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Hierarchical Question-Image Co-Attention for Visual Question Answering
• VQA: Visual Question Answering
• Learning to reinforcement learn
• Learning to Navigate in Complex Environments
• Building Generalizable Agents with a Realistic and Rich 3D Environment
• MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
• Grounded Language Learning in a Simulated 3D World
• Efficient Parallel Methods for Deep Reinforcement Learning
• Unifying Map and Landmark Based Representations for Visual Navigation
• Learning to Navigate in Cities Without a Map
• Interactive Grounded Language Acquisition and Generalization in a 2D World
• Visual Semantic Planning using Deep Successor Representations

Cited by in corpus (7)

• Self-Monitoring Navigation Agent via Auxiliary Progress Estimation
• Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
• The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation
• Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
• Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning
• Towards Navigation by Reasoning over Spatial Configurations
• Reinforcement Learning of Implicit and Explicit Control Flow in Instructions