mlsanityData to 14 Oct 2026

Influence of the Geometry of the world model on Curiosity Based Exploration

arXiv 2304.00188 ↗First posted 1 Apr 2023cs.AI cs.SY eess.SYcited by 1

On the map: World models → World models for language agents

Abstract (arXiv)

In human spatial awareness, 3-D projective geometry structures information integration and action planning through perspective taking within an internal representation space. The way different perspectives are related and transform a world model defines a specific perception and imagination scheme. In mathematics, such collection of transformations corresponds to a 'group', whose 'actions' characterize the geometry of a space. Imbuing world models with a group structure may capture different agents' spatial awareness and affordance schemes. We used group action as a special class of policies for perspective-dependent control. We explored how such geometric structure impacts agents' behavior, comparing how the Euclidean versus projective groups act on epistemic value in active inference, drive curiosity, and exploration behaviors. We formally demonstrate and simulate how the groups induce distinct behaviors in a simple search task. The projective group's nonlinear magnification of information transformed epistemic value according to the choice of frame, generating behaviors of approach toward an object of interest. The projective group structure within the agent's world model contains the Projective Consciousness Model, which is know to capture key features of consciousness. On the other hand, the Euclidean group had no effect on epistemic value : no action was better than the initial idle state. In structuring a priori an agent's internal representation, we show how geometry can play a key role in information integration and action planning.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 17 of its 95 references that are in the map. First posted on arXiv 1 Apr 2023.

Builds on

17 of 95 references.

References · 17

  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  2. 2020Planning to Explore via Self-Supervised World Modelscited by 368
  3. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 275
  4. 2020Active inference on discrete state-spaces: a synthesiscited by 92
  5. 2021Geometric Deep Learning and Equivariant Neural Networkscited by 65
  6. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  7. 2021Geometric Entropic Explorationcited by 32
  8. 2022Path integrals, particular kinds, and strange thingscited by 20
  9. 2020The Mathematical Structure of Integrated Information Theorycited by 5
  10. 2021Graph-Based Topological Exploration Planning in Large-Scale 3D Environmentscited by 5
  11. 2019Proactive Intention Recognition for Joint Human-Robot Search and Rescue Missions through Monte-Carlo Planning in POMDP Environmentscited by 4
  12. 2022On Non-Linear operators for Geometric Deep Learningcited by 3
5 more
  1. 2016Mysteries of Visual Experiencecited by 2
  2. 2021Exploratory State Representation Learningcited by 2
  3. 2018The Moon Illusion explained by the Projective Consciousness Modelcited by 1
  4. 2020Modeling the subjective perspective of consciousness and its role in the control of behaviourscited by 1
  5. 2021Combining the Projective Consciousness Model and Virtual Humans to assess ToM capacity in Virtual Reality: a proof-of-conceptcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2026Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
  2. 2026ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
  3. 2026From Perception to Action: Spatial AI Agents and World Models
  4. 2026Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
  5. 2026Active World-Model with 4D-informed Retrieval for Exploration and Awareness
  6. 2025From Curiosity to Competence: How World Models Interact with the Dynamics of Exploration
  7. 2025From 2D to 3D Cognition: A Brief Survey of General World Models
  8. 2023Inferring Hierarchical Structure in Multi-Room Maze Environments