Interaction Data and Passive Observation › Summary

Michael BrenndoerferJuly 3, 20262 min read
World Models HandbookAll chapters
Part 6 of 12Learning World Models at Scale
Chapter 33Interaction Data and Passive Observation › Summary
Reading section 8 of 10 · Summary · 2 minSection 8 of 10 · 2 min

Book contents

Section 8 of 10 · 2 min read

Interaction Data and Passive Observation › SummaryOne section · Sections in this chapter8 / 10 ↓
Reading tools Definitions & inline links

Choose your expertise level to adjust how many terms are explained. Beginners see more tooltips, experts see fewer to maintain reading flow. Hover over underlined terms for instant definitions.

Article links

Make inline references clickable

  • Interaction data records the agent's applied commands. It supports causal and counterfactual queries when the logging and action-selection assumptions rule out unobserved confounding.
  • Passive observation data (video, logs, scraped signals) may lack actions and may contain confounded behavior, so it cannot generally identify P(s′∣s,a)P(s' \mid s, a) on its own. It is useful for representation and dynamics priors, but interaction evidence is needed to identify a controllable transition function without stronger assumptions.
  • The behavior policy, initial-state distribution, and dynamics determine coverage. Missing support leaves transition behavior unidentified without further assumptions; good coverage is necessary but not sufficient for reliable planning.
  • Behavior policies shape observed data distributions. Action importance weighting targets a changed conditional action distribution only under absolute continuity and finite expectations, and it does not correct state-occupancy shift.
  • Interventions can expand coverage through random, uncertainty-driven, or task-conditioned exploration, but action diversity alone does not guarantee state coverage.
  • Passive pretraining and action-labeled fine-tuning can complement each other, as can joint objectives, but their benefit depends on domain alignment and downstream validation.
  • Data support constrains what the training observations identify. Model class, finite-sample error, partial observability, uncertainty calibration, and rollout compounding still matter inside that support.