Skip to main content
Search

# Flow Matching Policy

2 related articles

Subscribe to updates
  1. arXiv

    World models stop training a controller separately: LeWAM folds action prediction into one pass, lifting contact-rich success from 28.6% to 89.7%

    LeWAM trains visual representation, action-conditioned latent dynamics, and a stochastic policy in a single stage, raising planning success from 28.6% to 89.7% on contact-rich tasks and from 10.9% to 46.2% on long-horizon tasks while planning 32.3 times faster.

    University of California San DiegoJohn Brown UniversityUniversity of British ColumbiaETH ZurichBrown University
    Minghao Fu（First author）
    LeWAMJoint-Embedding Predictive ArchitectureLatent World ModelFlow Matching PolicyVisual Planning
  2. arXiv

    DexPolicy makes exploration noise an explicit function of training steps, lifting deterministic dexterous-manipulation success from 49.4% to 68.1% (FPO) in simulation and on hardware

    The work introduces DexPolicy, which in trajectory-guided dexterous manipulation reinforcement learning such as ViViDex makes the action-noise scale an explicit annealing function of training steps while holding loss, architecture, reward, and optimizer settings fixed; across PPO, critic-free GRPO continuation, and a flow-parameterized PPO variant (FPO), mean deterministic Target success over five YCB objects and three training seeds rises from 32.0% to 35.7%, 14.1% to 45.4%, and 49.4% to 68.1%, and on a RealMan RM75 arm with an Inspire/RH56 hand, 360 trials raise mean Target success from 8.3% to 43.3%, 10.0% to 63.3%, and 25.0% to 85.0%.

    DexPolicyScheduled Explorationdexterous robot hand manipulationProximal Policy OptimizationGRPO

You’re all caught up