Timezone: »

 
Overcoming Referential Ambiguity in language-guided goal-conditioned Reinforcement Learning
Hugo Caselles-Dupré · Olivier Sigaud · Mohamed CHETOUANI

@
in LaReL: Language and Reinforcement Learning »
Event URL: https://openreview.net/forum?id=Ijw_Am6DeQc »

Teaching an agent to perform new tasks using natural language can easily be hindered by ambiguities in interpretation. When a teacher provides an instruction to a learner about an object by referring to its features, the learner can misunderstand the teacher's intentions, for instance if the instruction ambiguously refer to features of the object, a phenomenon called referential ambiguity. We study how two concepts derived from cognitive sciences can help resolve those referential ambiguities: pedagogy (selecting the right instructions) and pragmatism (learning the preferences of the other agents using inductive reasoning). We apply those ideas to a teacher/learner setup with two artificial agents on a simulated robotic task (block-stacking). We show that these concepts improve sample efficiency for training the learner.

Keywords: goal-conditioned reinforcement learning · pragmatism · language-guided reinforcement learning · rational speech acts

Author Information

Hugo Caselles-Dupré (ISIR (Sorbonne Université))

Postdoc working on Reinforcement Learning and Developmental Robotics.

Olivier Sigaud (Sorbonne University)
Mohamed CHETOUANI (ISIR, UMR 7222)

More from the Same Authors