Abstract
This paper addresses a task in Interactive Task Learning (Laird et al. IEEE Intell Syst 32:6–21, 2017). The agent must learn to build towers which are constrained by rules, and whenever the agent performs an action which violates a rule the teacher provides verbal corrective feedback: e.g. “No, red blocks should be on blue blocks”. The agent must learn to build rule compliant towers from these corrections and the context in which they were given. The agent is not only ignorant of the rules at the start of the learning process, but it also has a deficient domain model, which lacks the concepts in which the rules are expressed. Therefore an agent that takes advantage of the linguistic evidence must learn the denotations of neologisms and adapt its conceptualisation of the planning domain to incorporate those denotations. We show that by incorporating constraints on interpretation that are imposed by discourse coherence into the models for learning (Hobbs in On the coherence and structure of discourse, Stanford University, Stanford, 1985; Asher et al. in Logics of conversation, Cambridge University Press, Cambridge, 2003), an agent which utilizes linguistic evidence outperforms a strong baseline which does not.
Highlights
The nascent field of Interactive Task Learning (ITL) aims to develop agents that can learn arbitrary new tasks through a combination of their own actions in the environment and an ongoing interaction with a teacher
We show how the semantics of discourse coherence can be leveraged to support learning for a type of dialogue move that has so far been ignored in ITL: the teacher corrects the agent’s latest action by specifying the constraint that it violates
We exploited the semantics of coherent discourse to jointly learn three tasks via natural language interaction with a teacher: how to refine an agents domain model to include unforeseen concepts as and when they are discovered via neologisms in the interaction; how to ground the domain model’s symbols to visual features; and how to infer a correct goal description, so as to construct valid sequential plans
Summary
The nascent field of Interactive Task Learning (ITL) aims to develop agents that can learn arbitrary new tasks through a combination of their own actions in the environment and an ongoing interaction with a teacher (see Laird et al [41] for a recent survey). Autonomous Agents and Multi-Agent Systems (2020) 34:54 instance, tasks where the set of possible options, or the specifications that govern correct behaviour, can change at any given time Motivated by such issues, ITL seeks to create agents that can learn after they are deployed, through situated interactions which are natural to the human domain expert that they interact with. There is an assumption that the teacher’s guidance is geared towards what the agent should do rather than what the agent just got wrong This emphasis effectively places a burden on teachers to recall and provide all the information that’s required to perform the appropriate action before the teacher observes the agent’s attempts to do it. To alleviate or recover from that burden, it would be useful to support, and learn from, a dialogue move where the teacher expresses why the agent’s latest action was suboptimal, or incorrect
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
