train-world-model-controller-vlm-relabelled-rollouts-then TEC-0220 · proposedTrain a world-model controller on VLM-relabelled rollouts, t
Relabel segments of a world-model policy's own on-policy rollouts with VLM-generated instructions, add a behaviour-cloning plus instruction-completion loss to the Dreamer objectives, and at inference let a frozen VLM planner emit sparse tex
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Relabel segments of a world-model policy's own on-policy rollouts with VLM-generated instructions, add a behaviour-cloning plus instruction-completion loss to the Dreamer objectives, and at inference let a frozen VLM planner emit sparse tex Filed by the drafting stage from Decoupling Planning and Control for Instructable Agents (2608.26788) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Official per-environment metrics on seven environments against controller-only, direct VLM action generation, a fine-tuned VLA (RT-2), DreamerV3, MAPPO and QMIX; ablation over instruction source (VLM-generated 11.1, template 9.9, clustered 8.9, random strings 8.3, none 8.2, environment-derived 11.4 on Minecraft Diamond); instruction-following accuracy 86-97% across planners.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.