Search papers, labs, and topics across Lattice.
The paper introduces "golden tickets," a method to improve pretrained generative robot policies by replacing stochastic initial noise sampling with a single, optimized constant noise vector. They use Monte-Carlo policy evaluation to search for these golden tickets without retraining the policy or introducing new networks, applicable to diffusion and flow matching policies. Experiments across 43 simulated and real-world robot manipulation tasks demonstrate improved performance in 38 tasks, with success rate improvements up to 58% in simulation and 60% in real-world settings, also showing benefits in multi-task scenarios.
Forget retraining: a single, carefully chosen noise vector can boost your robot's pre-trained policy performance by up to 60% in the real world.
What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from a Gaussian? We demonstrate that the performance of a pretrained, frozen diffusion or flow matching policy can be improved with respect to a downstream reward by swapping the sampling of initial noise from the prior distribution (typically isotropic Gaussian) with a well-chosen, constant initial noise input -- a golden ticket. We propose a search method to find golden tickets using Monte-Carlo policy evaluation that keeps the pretrained policy frozen, does not train any new networks, and is applicable to all diffusion/flow matching policies (and therefore many VLAs). Our approach to policy improvement makes no assumptions beyond being able to inject initial noise into the policy and calculate (sparse) task rewards of episode rollouts, making it deployable with no additional infrastructure or models. Our method improves the performance of policies in 38 out of 43 tasks across simulated and real-world robot manipulation benchmarks, with relative improvements in success rate by up to 58% for some simulated tasks, and 60% within 50 search episodes for real-world tasks. We also show unique benefits of golden tickets for multi-task settings: the diversity of behaviors from different tickets naturally defines a Pareto frontier for balancing different objectives (e.g., speed, success rates); in VLAs, we find that a golden ticket optimized for one task can also boost performance in other related tasks. We release a codebase with pretrained policies and golden tickets for simulation benchmarks using VLAs, diffusion policies, and flow matching policies.
