Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
Alban Laflaquière, Michael Garcia Ortiz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use consistent sensorimotor transitions in a static environment (MM) instead of inconsistent transitions in a moving environment (MEM) | Sensorimotor predictive network · Discrete world | D_topo | Improved |
| Use consistent sensorimotor transitions in a static environment (MM) instead of inconsistent transitions in a moving environment (MEM) | Sensorimotor predictive network · Discrete world | D_metric | Improved |
| Add environment displacements between consistent sensorimotor transitions (MME rather than MM) | Sensorimotor predictive network · Discrete world | D_metric | Improved |
| Use consistent transitions rather than transitions across environment movement (MM or MME rather than MEM) | Sensorimotor predictive network · Discrete world | sensorimotor prediction loss | Improved |
| Use consistent sensorimotor transitions in a static environment (MM) instead of inconsistent transitions in a moving environment (MEM) | Sensorimotor predictive network · Arm in a room | D_topo | Improved |
| Add environment displacements between consistent sensorimotor transitions (MME rather than MM) | Sensorimotor predictive network · Arm in a room | D_topo | Improved |
| Use consistent transitions rather than transitions across environment movement (MM or MME rather than MEM) | Sensorimotor predictive network · Arm in a room | sensorimotor prediction loss | Improved |
| Train with inconsistent transitions in a bounded room (MEM) | Sensorimotor predictive network · Arm in a room | D_topo | Mixed |
| Train with consistent transitions in a potentially ambiguous room without environment displacement (MM) | Sensorimotor predictive network · Arm in a room | D_topo | Hurt |
Closest papers by meaning
- End-to-End Egospheric Spatial Memory (ICLR 2021 · similarity 0.86)
- Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL (ICLR 2026 · similarity 0.86)
- Learning Awareness Models (ICLR 2018 · similarity 0.86)
- ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction (ICLR 2026 · similarity 0.86)
- Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences (NeurIPS 2024 · similarity 0.84)
- Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems (NeurIPS 2024 · similarity 0.84)
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.
