AI & ML
Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum
arXiv cs.RO0 views
arXiv:2611.17529v1 Announce Type: new Abstract: Image-goal planning with a frozen visual world model depends on how predicted observations are scored against the goal. Mean-squared error (MSE) between embeddings from a pretrained visual encoder can provide a useful signal near a goal, yet favor states across an obstacle that are visually similar to the goal and difficult to reach. We fit a small residual adapter on top of frozen I-JEPA embeddings to improve this latent goal cost. Starting near each goal, a planner collects trajectories from progressively wider regions of initial states. The adapter learns from the order of observations along successful trajectories, with additional comparisons inferred from failed rollouts. No task-specific progress labels are used for fitting, so the procedure can be applied to other goal-reaching tasks. DotWall and PointMaze are used in this work. In paired 50-case evaluations with identical starts, goals, world models, and planner settings, success increases from 54% to 98% in DotWall and from 82% to 96% in PointMaze. On 16 unseen DotWall layout-goal cases, the adapter fitted on one fixed layout improves agreement between latent-cost ordering and shortest legal-path ordering from 71.9% to 85.8%. The results indicate that planning experience can improve a frozen visual representation's goal cost without retraining the encoder or the world model.
Source:https://arxiv.org/abs/2611.17529PreviousRacing the Clock: Teaching VLNs Budget-Conditioned Object SearchNextTalk to Act: A Synthetic Multi-Turn Dialogue Benchmark for Human Intent Extraction and Action Planning in Robotics
Related posts
Cross-Benchmark Transfer from RL on Agentic Coding Tasks
0arXiv cs.SE
Programmable Distributions of Semantics-Preserving Variants for Evaluating Code Agents
0arXiv cs.SE
Kusner's conjecture on equilateral sets is false
0arXiv cs.NA
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
0arXiv stat.ML
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
0arXiv stat.ML
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
0arXiv stat.ML