Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
This work addresses referential ambiguity in language-guided RL for simulated robotic tasks, but it is incremental as it builds on existing cognitive science concepts.
The paper tackled the problem of referential ambiguity in language-guided goal-conditioned reinforcement learning by applying pedagogy and pragmatism concepts from cognitive sciences to a simulated robotic block-stacking task, resulting in improved sample efficiency for training the learner.
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.