How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning

Key points

• Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets.1
• To address these inefficiencies, we propose {SufficientPlan}, a simple deployment framework that requires no modification to pretrained world models or planner updates.1
• Its {Static-Context Reuse (SCR)} component caches observation and goal representations across search iterations while preserving candidate-dependent planning and selected actions.1
• Experiments across multiple world-model backbones and visual-control tasks show that SufficientPlan substantially reduces search budgets and planning latency while maintaining competitive control performance.1

Sources (1)

• [1]How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 01:40 PM

  We show that competitive task performance can be achieved without agreement with the Full-budget action, that sufficient budgets vary across model--task pairs, and that iterative planners repeatedly encode solve-invariant context.

  Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets.

Extractive summary: sentences quoted from the sources.