1. Asking for Knowledge : Training RL Agents to Query External Knowledge Using Language
- Author
-
Liu, Iou-Jen, Yuan, Xingdi, Côté, Marc-Alexandre, Oudeyer, Pierre-Yves, Schwing, Alexander G., Microsoft Research, Department of Electrical and Computer Engineering [Urbana] (University of Illinois), University of Illinois at Urbana-Champaign [Urbana], University of Illinois System-University of Illinois System, Flowing Epigenetic Robots and Systems (Flowers), Inria Bordeaux - Sud-Ouest, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Subjects
FOS: Computer and information sciences ,reinforcement learning ,Computer Science - Computation and Language ,Artificial Intelligence (cs.AI) ,question asking ,Computer Science - Artificial Intelligence ,question answering ,[INFO]Computer Science [cs] ,Computation and Language (cs.CL) ,natural language - Abstract
To solve difficult tasks, humans ask questions to acquire knowledge from external sources. In contrast, classical reinforcement learning agents lack such an ability and often resort to exploratory behavior. This is exacerbated as few present-day environments support querying for knowledge. In order to study how agents can be taught to query external knowledge via language, we first introduce two new environments: the grid-world-based Q-BabyAI and the text-based Q-TextWorld. In addition to physical interactions, an agent can query an external knowledge source specialized for these environments to gather information. Second, we propose the "Asking for Knowledge" (AFK) agent, which learns to generate language commands to query for meaningful knowledge that helps solve the tasks. AFK leverages a non-parametric memory, a pointer mechanism and an episodic exploration bonus to tackle (1) irrelevant information, (2) a large query language space, (3) delayed reward for making meaningful queries. Extensive experiments demonstrate that the AFK agent outperforms recent baselines on the challenging Q-BabyAI and Q-TextWorld environments., Comment: ICML 2022; Project page: https://ioujenliu.github.io/AFK/
- Published
- 2022