论文标题
IGLU GRIDWORLD：体现对话框的简单而快速的环境
IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents
论文作者
论文摘要
我们介绍了Iglu Gridworld：以可扩展的方式构建和评估语言有条件体现的代理的增强学习环境。环境具有视觉代理体现，通过协作，语言条件的RL和组合艰苦任务（3D块构建）空间具有交互式学习。
We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way. The environment features visual agent embodiment, interactive learning through collaboration, language conditioned RL, and combinatorically hard task (3d blocks building) space.
