Learning Manner of Execution from Partial Corrections
This addresses the challenge of integrating language feedback into robotic or AI systems for context-dependent tasks, but it appears incremental as it builds on existing concepts like coherence and planning.
The paper tackles the problem of an agent learning appropriate action execution manners (e.g., gently vs. vigorously) from context and verbal corrections, showing that it can perform symbol grounding to solve domain-level planning.
Some actions must be executed in different ways depending on the context. For example, wiping away marker requires vigorous force while wiping away almonds requires more gentle force. In this paper we provide a model where an agent learns which manner of action execution to use in which context, drawing on evidence from trial and error and verbal corrections when it makes a mistake (e.g., ``no, gently''). The learner starts out with a domain model that lacks the concepts denoted by the words in the teacher's feedback; both the words describing the context (e.g., marker) and the adverbs like ``gently''. We show that through the the semantics of coherence, our agent can perform the symbol grounding that's necessary for exploiting the teacher's feedback so as to solve its domain-level planning problem: to perform its actions in the current context in the right way.