Cognitive maps are generative programs
- URL: http://arxiv.org/abs/2504.20628v1
- Date: Tue, 29 Apr 2025 10:55:40 GMT
- Title: Cognitive maps are generative programs
- Authors: Marta Kryven, Cole Wyeth, Aidan Curtis, Kevin Ellis,
- Abstract summary: We show that cognitive maps can take the form of generative programs that exploit predictability and redundancy.<n>We describe a computational model that predicts human behavior in a variety of structured scenarios.<n>Our models leverage a Large Language Model as an embedding of human priors, implicitly learned through training on a vast corpus of human data.
- Score: 13.339419436986148
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Making sense of the world and acting in it relies on building simplified mental representations that abstract away aspects of reality. This principle of cognitive mapping is universal to agents with limited resources. Living organisms, people, and algorithms all face the problem of forming functional representations of their world under various computing constraints. In this work, we explore the hypothesis that human resource-efficient planning may arise from representing the world as predictably structured. Building on the metaphor of concepts as programs, we propose that cognitive maps can take the form of generative programs that exploit predictability and redundancy, in contrast to directly encoding spatial layouts. We use a behavioral experiment to show that people who navigate in structured spaces rely on modular planning strategies that align with programmatic map representations. We describe a computational model that predicts human behavior in a variety of structured scenarios. This model infers a small distribution over possible programmatic cognitive maps conditioned on human prior knowledge of the world, and uses this distribution to generate resource-efficient plans. Our models leverages a Large Language Model as an embedding of human priors, implicitly learned through training on a vast corpus of human data. Our model demonstrates improved computational efficiency, requires drastically less memory, and outperforms unstructured planning algorithms with cognitive constraints at predicting human behavior, suggesting that human planning strategies rely on programmatic cognitive maps.
Related papers
- Latent Diffusion Planning for Imitation Learning [78.56207566743154]
Latent Diffusion Planning (LDP) is a modular approach consisting of a planner and inverse dynamics model.<n>By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data.<n>On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches.
arXiv Detail & Related papers (2025-04-23T17:53:34Z) - Human-like conceptual representations emerge from language prediction [72.5875173689788]
Large language models (LLMs) trained exclusively through next-token prediction over language data exhibit remarkably human-like behaviors.<n>Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized?<n>Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts.<n>These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding.
arXiv Detail & Related papers (2025-01-21T23:54:17Z) - How language models extrapolate outside the training data: A case study in Textualized Gridworld [32.5268320198854]
We show that conventional approaches, including next token prediction and Chain of Thought finetuning, fail to extrapolate in larger, unseen environments.<n>We propose cognitive maps for path planning, a novel CoT framework that simulates humanlike mental representations.<n>Our finding that these cognitive maps require specialized training schemes opens up important questions about developing general-purpose cognitive maps in language models.
arXiv Detail & Related papers (2024-06-21T16:10:05Z) - Achieving mouse-level strategic evasion performance using real-time
computational planning [59.60094442546867]
Planning is an extraordinary ability in which the brain imagines and then enacts evaluated possible futures.
We develop a more efficient biologically-inspired planning algorithm, TLPPO, based on work on how the ecology of an animal governs the value of spatial planning.
We compare the performance of a real-time agent using TLPPO against the performance of live mice, all tasked with evading a robot predator.
arXiv Detail & Related papers (2022-11-04T18:34:36Z) - Map Induction: Compositional spatial submap learning for efficient
exploration in novel environments [25.00757828975447]
We show that humans explore new environments efficiently by inferring the structure of unobserved spaces.
Using a new behavioral Map Induction Task, we demonstrate that this computational framework explains human exploration behavior better than non-inductive models.
arXiv Detail & Related papers (2021-10-23T21:23:04Z) - Procedure Planning in Instructional Videosvia Contextual Modeling and
Model-based Policy Learning [114.1830997893756]
This work focuses on learning a model to plan goal-directed actions in real-life videos.
We propose novel algorithms to model human behaviors through Bayesian Inference and model-based Imitation Learning.
arXiv Detail & Related papers (2021-10-05T01:06:53Z) - Automatic discovery and description of human planning strategies [0.7734726150561086]
We leverage AI for strategy discovery for understanding human planning.
Our algorithm, called Human-Interpret, uses imitation learning to describe process-tracing data.
We find that the descriptions of human planning strategies obtained automatically are about as understandable as human-generated descriptions.
arXiv Detail & Related papers (2021-09-29T15:20:16Z) - Towards a Predictive Processing Implementation of the Common Model of
Cognition [79.63867412771461]
We describe an implementation of the common model of cognition grounded in neural generative coding and holographic associative memory.
The proposed system creates the groundwork for developing agents that learn continually from diverse tasks as well as model human performance at larger scales.
arXiv Detail & Related papers (2021-05-15T22:55:23Z) - Control of mental representations in human planning [38.227123320091046]
Two aspects of human planning stand out its efficiency, even in complex environments, and its flexibility, even in changing environments.
Efficiency is especially impressive because directly computing an optimal plan is intractable, even for modestly complex tasks, and yet people successfully solve myriad problems despite limited cognitive resources.
Here, we propose that mental representations can be controlled and that this provides opportunities to adaptively simplify problems so they can be more easily reasoned about.
arXiv Detail & Related papers (2021-05-14T16:39:31Z) - Deep Interpretable Models of Theory of Mind For Human-Agent Teaming [0.7734726150561086]
We develop an interpretable modular neural framework for modeling the intentions of other observed entities.
We demonstrate the efficacy of our approach with experiments on data from human participants on a search and rescue task in Minecraft.
arXiv Detail & Related papers (2021-04-07T06:18:58Z) - Forethought and Hindsight in Credit Assignment [62.05690959741223]
We work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models.
We investigate the best use of models in planning, primarily focusing on the selection of states in which predictions should be (re)-evaluated.
arXiv Detail & Related papers (2020-10-26T16:00:47Z)
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.