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.
翻译:我们介绍了IGLU网状世界:一个强化学习环境,用于以可扩展的方式建设和评价有条件的语言装饰剂。 环境的特征是视觉剂化、通过协作的互动学习、用语言调节RL和组合式艰苦任务(3d块建筑)空间。