Learning to act: qualitative learning of deterministic action models

Bolander, Thomas; Gierasimczuk, Nina

doi:10.1093/logcom/exx036

Cited by 7 publications

(4 citation statements)

References 19 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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'.…”

mentioning

confidence: 99%

Truth-Tracking by Belief Revision

2018

Self Cite

View full text Add to dashboard Cite

Abstract.We study the learning power of iterated belief revision methods. Successful learning is understood as convergence to correct, i.e., true, beliefs. We focus on the issue of universality: whether or not a particular belief revision method is able to learn everything that in principle is learnable. We provide a general framework for interpreting belief revision policies as learning methods. We focus on three popular cases: conditioning, lexicographic revision, and minimal revision. Our main result is that conditioning and lexicographic revision can drive a universal learning mechanism, provided that the observations include only and all true data, and provided that a non-standard, i.e., non-well-founded prior plausibility relation is allowed. We show that a standard, i.e., well-founded belief revision setting is in general too narrow to guarantee universality of any learning method based on belief revision. We also show that minimal revision is not universal. Finally, we consider situations in which observational errors (false observations) may occur. Given a fairness condition, which says that only finitely many errors occur, and that every error is eventually corrected, we show that lexicographic revision is still universal in this setting, while the other two methods are not.

show abstract

mentioning

confidence: 99%

Truth-Tracking by Belief Revision

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…With this regard, learning as belief propagation can be understood as transitioning from non-deterministic to deterministic action models, incrementally increasing the amount of determinism. This approach has been successfully implemented using dynamic epistemic logic for learning different types of propositional action models (Bolander & Gierasimczuk, 2018).…”

Section: Learning As Belief Propagationmentioning

confidence: 99%

A Comprehensive Framework for Learning Declarative Action Models

Aineto

Jiménez

Onaindía

2022

jair

View full text Add to dashboard Cite

A declarative action model is a compact representation of the state transitions of dynamic systems that generalizes over world objects. The specification of declarative action models is often a complex hand-crafted task. In this paper we formulate declarative action models via state constraints, and present the learning of such models as a combinatorial search. The comprehensive framework presented here allows us to connect the learning of declarative action models to well-known problem solving tasks. In addition, our framework allows us to characterize the existing work in the literature according to four dimensions: (1) the target action models, in terms of the state transitions they define; (2) the available learning examples; (3) the functions used to guide the learning process, and to evaluate the quality of the learned action models; (4) the learning algorithm. Last, the paper lists relevant successful applications of the learning of declarative actions models and discusses some open challenges with the aim of encouraging future research work.

show abstract

“…This is in contrast with identifiability in the limit [30], which holds for any learning process in which the learner converges to the right solution after seeing finitely many inputs, but does not necessarily know at which point convergence takes place. In formal learning theory, a set that enables finite identification is called a definite finite tell-tale set (DFTT for short, see [42,28,27], for an application in action learning see [14]). We adapt this notion to our setting.…”

Section: Behavioural Correctness and Learnabilitymentioning

confidence: 99%

“…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.…”

Section: Related Workmentioning

confidence: 99%

Learning to Act and Observe in Partially Observable Domains

Bolander,

Gierasimczuk,

Liberman

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We consider a learning agent in a partially observable environment, with which the agent has never interacted before, and about which it learns both what it can observe and how its actions affect the environment. The agent can learn about this domain from experience gathered by taking actions in the domain and observing their results. We present learning algorithms capable of learning as much as possible (in a well-defined sense) both about what is directly observable and about what actions do in the domain, given the learner's observational constraints. We differentiate the level of domain knowledge attained by each algorithm, and characterize the type of observations required to reach it. 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.

show abstract

Learning to act: qualitative learning of deterministic action models

Cited by 7 publications

References 19 publications

Truth-Tracking by Belief Revision

Truth-Tracking by Belief Revision

A Comprehensive Framework for Learning Declarative Action Models

Learning to Act and Observe in Partially Observable Domains

Contact Info

Product

Resources

About