ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule

We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be suboptimal given a budget on the number of time steps. We introduce Adaptive Reparameterized Time (ART) that controls the clock speed of a reparameterized time variable, leading to a time change and uneven timesteps along the sampling trajectory while preserving the terminal time. The objective is to minimize the aggregate error arising from the discretized Euler scheme. We derive a randomized control companion, ART-RL, and formulate time change as a continuous-time reinforcement learning (RL) problem with Gaussian policies. We then prove that solving ART-RL recovers the optimal ART schedule, which in turn enables practical actor--critic updates to learn the latter in a data-driven way. Empirically, based on the official EDM pipeline, ART-RL improves Fréchet Inception Distance on CIFAR-10 over a wide range of budgets and transfers to AFHQv2, FFHQ, and ImageNet without the need of retraining.

Exploration versus exploitation in reinforcement learning: a stochastic control approach

We consider reinforcement learning (RL) in continuous time and study the problem of achieving the best trade-off between exploration of a black box environment and exploitation of current knowledge. We propose an entropy-regularized reward function involving the differential entropy of the distributions of actions, and motivate and devise an exploratory formulation for the feature dynamics that captures repetitive learning under exploration. The resulting optimization problem is a resurrection of the classical relaxed stochastic control. We carry out a complete analysis of the problem in the linear--quadratic (LQ) case and deduce that the optimal control distribution for balancing exploitation and exploration is Gaussian. This in turn interprets and justifies the widely adopted Gaussian exploration in RL, beyond its simplicity for sampling. Moreover, the exploitation and exploration are reflected respectively by the mean and variance of the Gaussian distribution. We also find that a more random environment contains more learning opportunities in the sense that less exploration is needed, other things being equal. As the weight of exploration decays to zero, we prove the convergence of the solution to the entropy-regularized LQ problem to that of the classical LQ problem. Finally, we characterize the cost of exploration, which is shown to be proportional to the entropy regularization weight and inversely proportional to the discount rate in the LQ case.