arXiv:2605.21282v3 Announce Type: replace-cross
Abstract: Combining entropy regularisation with mirror descent in online off-policy reinforcement learning requires expressive policies with efficient sampling and explicit entropy control. Gaussian policies struggle to represent multimodal targets, whereas generative policies often require iterative sampling or lack tractable entropy estimates. We introduce Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that combines MeanFlow-based noise-to-action mappings with Gaussian reparameterisation. The latent mapping captures diverse action modes, while a learnable conditional Gaussian scale provides an analytic entropy lower bound. We use this bound to regulate stochasticity alongside direct value guidance and advantage-weighted MeanFlow regression, enabling entropy-regularised mirror-descent learning with one-step policies. Across seven MuJoCo benchmarks, SMFP achieves strong performance against Gaussian and generative baselines with single-step inference. Additional experiments demonstrate multimodal action modelling and effective exploration in sparse-reward navigation.
Abstract: Combining entropy regularisation with mirror descent in online off-policy reinforcement learning requires expressive policies with efficient sampling and explicit entropy control. Gaussian policies struggle to represent multimodal targets, whereas generative policies often require iterative sampling or lack tractable entropy estimates. We introduce Stochastic MeanFlow Policies (SMFP), a one-step generative policy class that combines MeanFlow-based noise-to-action mappings with Gaussian reparameterisation. The latent mapping captures diverse action modes, while a learnable conditional Gaussian scale provides an analytic entropy lower bound. We use this bound to regulate stochasticity alongside direct value guidance and advantage-weighted MeanFlow regression, enabling entropy-regularised mirror-descent learning with one-step policies. Across seven MuJoCo benchmarks, SMFP achieves strong performance against Gaussian and generative baselines with single-step inference. Additional experiments demonstrate multimodal action modelling and effective exploration in sparse-reward navigation.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article: