Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Efficient state-space modularization for planning: theory, behavioral and neural signatures
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fit logarithmic instead of linear function | compression factor vs route length · U. Toronto empirical data | R2: 0.46 -> 0.69 | Helped |
| fit logarithmic instead of linear function | simulated modularized compression factor · London Soho, routes of 1 to 10 states | R2: 0.72 -> 0.82 | Helped |
| compare degree centrality to betweenness and closeness as correlate of local planning entropy change | optimal modularization · London Soho simulated trajectories | Spearman correlation: 0.79 | Helped |
| apply optimal modularization versus no modularization to simulated striatal neurons | firing rate scaled with local planning entropy · T-maze task | task-bracketing in firing | Helped |
| use optimal modularization of operant task state-space | start/stop code description lengths · operant conditioning lever task | description length of start vs stop codes | Helped |
Closest papers by meaning
- Compact task representations as a normative model for higher-order brain activity (NeurIPS 2020 · similarity 0.89)
- Actionable Neural Representations: Grid Cells from Minimal Constraints (ICLR 2023 · similarity 0.87)
- Planning with Biological Neurons and Synapses (AAAI 2022 · similarity 0.87)
- Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning (ICML 2024 · similarity 0.85)
- HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning (NeurIPS 2026 · similarity 0.85)
- Neural networks are more modular than single neurons suggest (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.