Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 9 of its 20 references that are in the map. First posted on arXiv 26 Sep 2022.
Builds on
9 of 20 references.
References · 9
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2017Hindsight Experience Replaycited by 1,096
- 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 337
- 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 83
- 2020Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Explorationcited by 68
- 2022Inferring Rewards from Language in Contextcited by 50
- 2022Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agentscited by 3
- 2022Pedagogical Demonstrations and Pragmatic Learning in Artificial Tutor-Learner Interactionscited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.