Learning Actions Models: Qualitative Approach

Abstract

In dynamic epistemic logic, actions are described using action models. In this paper we introduce a framework for studying learnability of action models from observations. We present first results concerning propositional action models. First we check two basic learnability criteria: finite identifiability (conclusively inferring the appropriate action model in finite time) and identifiability in the limit (inconclusive convergence to the right action model). We show that deterministic actions are finitely identifiable, while non-deterministic actions require more learning power-they are identifiable in the limit. We then move on to a particular learning method, which proceeds via restriction of a space of events within a learning-specific action model. This way of learning closely resembles the well-known update method from dynamic epistemic logic. We introduce several different learning methods suited for finite identifiability of particular types of deterministic actions.

Truth-Tracking by Belief Revision

“…1 The emergence of the stronger epistemic state of irrevocable knowledge can be linked to a more restrictive kind of identifiability, finite identifiability [see 19,20,27]. It has also been recently investigated in the context of action learning in dynamic epistemic logic [16,17]. 2 Note that we interpret s t as 's is at least as plausible as t'.…”

Learning to Act and Observe in Partially Observable Domains

“…The algorithms use dynamic epistemic logic (DEL) to represent the learned domain information symbolically. Our work continues that of Bolander and Gierasimczuk (2015), which developed DEL-based learning algorithms based to learn domain information in fully observable domains.…”

“…This work builds upon the framework by Bolander and Gierasimczuk [13,14], where two basic learnability criteria for actions were studied: finite identifiability (conclusively inferring a representation of the correct action in finite time) and identifiability in the limit (inconclusive convergence to a representation of the right action). It has been shown that deterministic actions are finitely identifiable, while arbitrary (nondeterministic) actions are only identifiable in the limit, in the fully observable setting.…”

Logic, Probability and Action: A Situation Calculus Perspective

“…Indeed, in addition to approaches such as [22,75], there have been a number of advances recently on learning dynamic representations (e.g., [68]), which might provide fertile ground to lift such ideas for cognitive robotics. Computability results for qualitative learning in dynamic epistemic logic has been studied in [16]. Recently, proper + knowledge bases were shown to be polynomial-time learnable for querying tasks [5].…”