Interpreting systems as solving POMDPs: a step towards a formal understanding of agency

• URL: http://arxiv.org/abs/2209.01619v1
• Date: Sun, 4 Sep 2022 13:40:33 GMT
• Title: Interpreting systems as solving POMDPs: a step towards a formal understanding of agency
• Abstract summary: We propose a notion of interpretation not just in terms of beliefs but in terms of goals and actions. An agent is then a system together with an interpretation of this system as a POMDP solution.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Under what circumstances can a system be said to have beliefs and goals, and how do such agency-related features relate to its physical state? Recent work has proposed a notion of interpretation map, a function that maps the state of a system to a probability distribution representing its beliefs about an external world. Such a map is not completely arbitrary, as the beliefs it attributes to the system must evolve over time in a manner that is consistent with Bayes' theorem, and consequently the dynamics of a system constrain its possible interpretations. Here we build on this approach, proposing a notion of interpretation not just in terms of beliefs but in terms of goals and actions. To do this we make use of the existing theory of partially observable Markov processes (POMDPs): we say that a system can be interpreted as a solution to a POMDP if it not only admits an interpretation map describing its beliefs about the hidden state of a POMDP but also takes actions that are optimal according to its belief state. An agent is then a system together with an interpretation of this system as a POMDP solution. Although POMDPs are not the only possible formulation of what it means to have a goal, this nevertheless represents a step towards a more general formal definition of what it means for a system to be an agent.

Related papers

• Ceci n'est pas une pipe: AI systems as semantic abstractions [0.0]
  An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation.<n>We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations.
  arXiv  Detail & Related papers  (2026-07-10T15:05:28Z)
• Radical AI Interpretability [0.0]
  We develop a framework for interpreting AI systems as agents.<n>We draw on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
  arXiv  Detail & Related papers  (2026-06-25T01:58:38Z)
• The Khipu Problem: Institutional Legibility Under Distributed Cognition [0.0]
  This paper introduces the khipu problem for distributed AI: the record can survive while the reading practice needed to interpret it decays.<n>Logs, traces, model versions, tool calls, outputs, and approval artifacts may remain available while the institutional capacity to read them as parts of one coherent cognitive episode disappears.<n>We argue that this failure is better understood as loss of interpretive continuity than as ordinary lack of observability.
  arXiv  Detail & Related papers  (2026-05-06T16:51:52Z)
• A Unified Formal Theory on the Logical Limits of Symbol Grounding [0.65268245109828]
  We show that meaning within a formal system must arise from a process that is external, dynamic, and non-algorithmic.<n>We extend this limitation to systems with any finite, static set of pre-established meanings.
  arXiv  Detail & Related papers  (2025-09-24T05:40:08Z)
• A "good regulator theorem" for embodied agents [0.0]
  Conant and Ashby claimed that "every good regulator of a system must be a model of that system"<n>Here we show that a similar intuition can be fleshed out in a different way.<n>It is possible for an observer to interpret it as having "beliefs" about its environment.
  arXiv  Detail & Related papers  (2025-08-04T16:11:31Z)
• Opacity as Authority: Arbitrariness and the Preclusion of Contestation [0.0]
  Article redefines arbitrariness not as a normative flaw or a symptom of domination, but as a functional mechanism structuring human systems and interactions.<n>Building on Ferdinand de Saussure's concept of l'arbitraire du signe, the analysis extends this principle beyond language to demonstrate its cross-domain applicability.
  arXiv  Detail & Related papers  (2025-07-25T19:10:35Z)
• Agency Is Frame-Dependent [94.91580596320331]
  Agency is a system's capacity to steer outcomes toward a goal. We argue that agency is fundamentally frame-dependent. We conclude that any basic science of agency requires frame-dependence.
  arXiv  Detail & Related papers  (2025-02-06T08:34:57Z)
• Propositional Interpretability in Artificial Intelligence [0.0]
  I argue for the importance of propositional interpretability, which involves interpreting a system's mechanisms and behavior in terms of propositional attitudes. A central challenge is what I call thought logging: creating systems that log all of the relevant propositional attitudes in an AI system over time.
  arXiv  Detail & Related papers  (2025-01-27T03:06:06Z)
• A Note on an Inferentialist Approach to Resource Semantics [48.65926948745294]
  'Inferentialism' is the view that meaning is given in terms of inferential behaviour. This paper shows how 'inferentialism' enables a versatile and expressive framework for resource semantics.
  arXiv  Detail & Related papers  (2024-05-10T14:13:21Z)
• Isopignistic Canonical Decomposition via Belief Evolution Network [12.459136964317942]
  We propose an isopignistic transformation based on the belief evolution network. This decomposition offers a reverse path between the possibility distribution and its isopignistic mass functions. This paper establishes a theoretical basis for building general models of artificial intelligence based on probability theory, Dempster-Shafer theory, and possibility theory.
  arXiv  Detail & Related papers  (2024-05-04T12:39:15Z)
• Inferentialist Resource Semantics [48.65926948745294]
  This paper shows how inferentialism enables a versatile and expressive framework for resource semantics. How inferentialism seamlessly incorporates the assertion-based approach of the logic of Bunched Implications. This integration enables reasoning about shared and separated resources in intuitive and familiar ways.
  arXiv  Detail & Related papers  (2024-02-14T14:54:36Z)
• A Systems-Theoretical Formalization of Closed Systems [47.99822253865054]
  There is a lack of formalism for some key foundational concepts in systems engineering. One of the most recently acknowledged deficits is the inadequacy of systems engineering practices for intelligent systems.
  arXiv  Detail & Related papers  (2023-11-16T19:01:01Z)
• A Semantic Approach to Decidability in Epistemic Planning (Extended Version) [72.77805489645604]
  We use a novel semantic approach to achieve decidability. Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity. We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
  arXiv  Detail & Related papers  (2023-07-28T11:26:26Z)
• On Nested Justification Systems (full version) [13.76408511310322]
  Nested justification systems, first introduced by Denecker et al., allow for the composition of justification systems. We show in this paper that the original semantics for nested justification systems lead to the loss of information relevant for explanations. Furthermore, we show how nested justification systems allow representing fixpoint definitions.
  arXiv  Detail & Related papers  (2022-05-09T20:23:22Z)
• Interpreting Dynamical Systems as Bayesian Reasoners [0.0]
  A central concept in active inference is that the internal states of a physical system parametrise probability measures over states of the external world. Here we begin the development of a general theory that would tell us when it is appropriate to interpret states as representing beliefs in this way.
  arXiv  Detail & Related papers  (2021-12-27T05:44:47Z)
• Quantum realism: axiomatization and quantification [77.34726150561087]
  We build an axiomatization for quantum realism -- a notion of realism compatible with quantum theory. We explicitly construct some classes of entropic quantifiers that are shown to satisfy almost all of the proposed axioms.
  arXiv  Detail & Related papers  (2021-10-10T18:08:42Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)
• Distributional Formal Semantics [0.18352113484137625]
  We propose a Distributional Formal Semantics that integrates distributionality into a formal semantic system on the level of formal models. This approach offers probabilistic, distributed meaning representations that are also inherently compositional. We show how these representations allow for probabilistic inference, and how the information-theoretic notion of "information" naturally follows from it.
  arXiv  Detail & Related papers  (2021-03-02T13:38:00Z)
• How to marry a star: probabilistic constraints for meaning in context [11.670687428360688]
  We derive a notion of 'word meaning in context' that characterizes meaning as both intensional and conceptual. We introduce a framework for specifying local as well as global constraints on word meaning in context, together with their interactions. We represent sentence meaning as a'situation description system', a probabilistic model which takes utterance understanding to be the mental process of describing to oneself one or more situations that would account for an observed utterance.
  arXiv  Detail & Related papers  (2020-09-16T21:11:23Z)
• Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness? [58.13152510843004]
  With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. What is interpretability, and what constitutes a high-quality interpretation? We call for more clearly differentiating between different desired criteria an interpretation should satisfy, and focus on the faithfulness criteria.
  arXiv  Detail & Related papers  (2020-04-07T20:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.