Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy
Abstract
Online reinforcement learning (RL) fine-tuning of pretrained flow-matching vision-language-action (VLA) policies promises robots that keep learning after deployment, but continued updates frequently destroy competence on individual tasks while the aggregate still looks healthy. We study this failure mode, which we call task collapse, under a matched small-compute budget on LIBERO-10 with a 450M-parameter SmolVLA policy trained by PPO in the stochastic (SDE) sampling regime. Three exploration-noise policies differ in a single live variable: a fixed noise scale, a learned noise network in the style of ReinFlow, and an uncertainty-gated controller that redistributes exploration across task streams from task-agnostic novelty and competence signals, without task labels or episode boundaries. Under the pooled definition, fixed noise collapses tasks in two of three seeds and learned noise in every seed measured to iteration 200, while the controller collapses none in any of its three seeds. Measured parameter displacement confirms that the controller's action expert continues to change, while its mean applied noise is close to the fixed scale in the available logs. The matched comparison supports the controller's effect on task preservation; the separate contributions of its adaptation across states and over time are not disentangled. A lower fixed scale slows the decline but does not stop it. No arm improves on the behavior-cloning baseline in this budget. Two properties of that regime are measured beside this result rather than offered as its cause: following the reference recipe, training runs in bfloat16 with no fp32 master copy, under which 96.02% of the action expert's elements stay bit-identical across three consecutive iterations, and an fp32 master copy at the reference learning rate collapses both arms in a single-seed observation. We release measurement tools for per-task collapse under four definitions, run-to-run rescoring noise and instrument tares.
Then back it, or bet against it.
Related papers
Open the market on this paper to see 7 more related papers.