mlsanityData to 14 Oct 2026

The syntax and semantics of goals

arXiv 2609.19448 ↗First posted 16 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In both cognitive science and computer science, goals are conceptualized as cognitive states that flexibly combine with world knowledge to organize and specify purposeful behavior. In this way, goals are compositional representations whose content relates to rational behavior. We here draw attention to goals as representations and their content because it highlights a parallel with other areas in cognitive science - in particular, the syntax-semantics interface in linguistics and logic - while also foregrounding foundational questions about the expressivity, design, and efficiency of different goal representations. For example, goals are typically taken as fixed and imposing constraints on desirable behaviors, but we can also identify constraints on goal representations themselves, such as whether a particular goal language is sufficiently expressive to capture behaviors of interest, or whether different goal representations capture the same behavior. Here, we synthesize work that aims to characterize the properties of different goal representations and suggest these are points of a broader design space. We close by discussing how distinguishing the form and meaning of goals can elucidate the implicit assumptions we make about goals, inform the study of interactions between higher-level cognition and motivation, and isolate axes of variation for different conceptions of goals.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 82 references that are in the map. First posted on arXiv 16 Sep 2026.

Builds on

20 of 82 references.

References · 20

  1. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  2. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  3. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 369
  4. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 191
  5. 2023A Definition of Continual Reinforcement Learningcited by 101
  6. 2020The Value Equivalence Principle for Model-Based Reinforcement Learningcited by 94
  7. 2021On the Expressivity of Markov Rewardcited by 71
  8. 2017Environment-Independent Task Specifications via GLTLcited by 67
  9. 2020A Boolean Task Algebra for Reinforcement Learningcited by 48
  10. 2021People construct simplified mental representations to plancited by 47
  11. 2021Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent Statescited by 43
  12. 2016Unifying task specification in reinforcement learningcited by 41
8 more
  1. 2023Continual Learning as Computationally Constrained Reinforcement Learningcited by 37
  2. 2022Settling the Reward Hypothesiscited by 33
  3. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  4. 2025General agents contain world modelscited by 17
  5. 2024Goals as Reward-Producing Programscited by 14
  6. 2025Evolution and The Knightian Blindspot of Machine Learningcited by 11
  7. 2025Optimizing Return Distributions with Distributional Dynamic Programmingcited by 10
  8. 2025Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPscited by 2

Built on by

Not cited yet.