Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language
This addresses the limitation of classical RL agents in acquiring external knowledge, which is incremental as it builds on existing RL and language methods.
The paper tackles the problem of enabling reinforcement learning agents to query external knowledge using language, by introducing two new environments (Q-BabyAI and Q-TextWorld) and proposing the AFK agent, which outperforms baselines on these tasks.
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.