Search for: All records

Abstract A data‐driven emulator for the baroclinic double gyre ocean simulation is presented in this study. Traditional numerical simulations using partial differential equations (PDEs) often require substantial computational resources, hindering real‐time applications and inhibiting model scalability. This study presents a novel approach employing Fourier neural operators to address these challenges in an idealized double‐gyre ocean simulation. We propose a deep learning approach capable of learning the underlying dynamics of the ocean system, complementing the classical methods. Additionally, we show how Fourier neural operators allow us to train the network at one resolution and generate ensembles at a different resolution. We find that there is an intermediate time scale where the prediction skill is maximized. 

Learning a dynamical system requires stabilizing the unknown dynamics to avoid state blow-ups. However, the standard reinforcement learning (RL) methods lack formal stabilization guarantees, which limits their applicability for the control of real-world dynamical systems. We propose a novel policy optimization method that adopts Krasovskii's family of Lyapunov functions as a stability constraint. We show that solving this stability-constrained optimization problem using a primal-dual approach recovers a stabilizing policy for the underlying system even under modeling error. Combining this method with model learning, we propose a model-based RL framework with formal stability guarantees, Krasovskii-Constrained Reinforcement Learning (KCRL). We theoretically study KCRL with kernel-based feature representation in model learning and provide a sample complexity guarantee to learn a stabilizing controller for the underlying system. Further, we empirically demonstrate the effectiveness of KCRL in learning stabilizing policies in online voltage control of a distributed power system. We show that KCRL stabilizes the system under various real-world solar and electricity demand profiles, whereas standard RL methods often fail to stabilize. 

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $$\tilde{O}(d^{3/2}H^{3/2}\sqrt{T})$$, where $$d$$ is the dimension of the feature mapping, $$H$$ is the planning horizon, and $$T$$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.\footnote{Our code is available at \url{https://github.com/hmishfaq/LMC-LSVI}} 

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $$\tilde{O}(d^{3/2}H^{3/2}\sqrt{T})$$, where $$d$$ is the dimension of the feature mapping, $$H$$ is the planning horizon, and $$T$$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.\footnote{Our code is available at \url{https://github.com/hmishfaq/LMC-LSVI}} 

SUMMARY We introduce a scheme for probabilistic hypocentre inversion with Stein variational inference. Our approach uses a differentiable forward model in the form of a physics informed neural network, which we train to solve the Eikonal equation. This allows for rapid approximation of the posterior by iteratively optimizing a collection of particles against a kernelized Stein discrepancy. We show that the method is well-equipped to handle highly multimodal posterior distributions, which are common in hypocentral inverse problems. A suite of experiments is performed to examine the influence of the various hyperparameters. Once trained, the method is valid for any seismic network geometry within the study area without the need to build traveltime tables. We show that the computational demands scale efficiently with the number of differential times, making it ideal for large-N sensing technologies like Distributed Acoustic Sensing. The techniques outlined in this manuscript have considerable implications beyond just ray tracing procedures, with the work flow applicable to other fields with computationally expensive inversion procedures such as full waveform inversion. 

The recent deep learning revolution has created enormous opportunities for accelerating compute capabilities in the context of physics-based simulations. In this article, we propose EikoNet, a deep learning approach to solving the Eikonal equation, which characterizes the first-arrival-time field in heterogeneous 3-D velocity structures. Our grid-free approach allows for rapid determination of the travel time between any two points within a continuous 3-D domain. These travel time solutions are allowed to violate the differential equation--which casts the problem as one of optimization--with the goal of finding network parameters that minimize the degree to which the equation is violated. In doing so, the method exploits the differentiability of neural networks to calculate the spatial gradients analytically, meaning that the network can be trained on its own without ever needing solutions from a finite-difference algorithm. EikoNet is rigorously tested on several velocity models and sampling methods to demonstrate robustness and versatility. Training and inference are highly parallelized, making the approach well-suited for GPUs. EikoNet has low memory overhead and further avoids the need for travel-time lookup tables. The developed approach has important applications to earthquake hypocenter inversion, ray multipathing, and tomographic modeling, as well as to other fields beyond seismology where ray tracing is essential.