Search NASA⌕ Search

SEARCH · Search NASA

Results for “Offline Reinforcement Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

42 records · Page 3

Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e

We introduce a novel Proximal Policy Optimization (PPO) algorithm aimed at addressing the challenge of maintaining a uniform proton beam intensity delivery in the Muon to Electron Conversion Experiment (Mu2e) at Fermi National Accelerator Laboratory (Fermilab). Our primary objective is to regulate the spill process to ensure a consistent intensity profile, with the ultimate goal of creating an automated controller capable of providing real-time feedback and calibration of the Spill Regulation System (SRS) parameters on a millisecond timescale. We treat the Mu2e accelerator system as a Markov Decision Process suitable for Reinforcement Learning (RL), utilizing PPO to reduce bias and enhance training stability. A key innovation in our approach is the integration of a neuralized Proportional-Integral-Derivative (PID) controller into the policy function, resulting in a significant improvement in the Spill Duty Factor (SDF) by 13.6%, surpassing the performance of the current PID controller baseline by an additional 1.6%. This paper presents the preliminary offline results based on a differentiable simulator of the Mu2e accelerator. It paves the groundwork for real-time implementations and applications, representing a crucial step towards automated proton beam intensity control for the Mu2e experiment.

43 PARTICLE ACCELERATORS↗

Neural network approaches for parameterized optimal control

Here, we consider numerical approaches for deterministic, finite-dimensional optimal control problems whose dynamics depend on unknown or uncertain parameters. We seek to amortize the solution over a set of relevant parameters in an offline stage to enable rapid decision-making and be able to react to changes in the parameter in the online stage. To tackle the curse of dimensionality arising when the state and/or parameter are high-dimensional, we represent the policy using neural networks. We compare two training paradigms: First, our model-based approach leverages the dynamics and definition of the objective function to learn the value function of the parameterized optimal control problem and obtain the policy using a feedback form. Second, we use actor-critic reinforcement learning to approximate the policy in a data-driven way. Using an example involving a two-dimensional convection-diffusion equation, which features high-dimensional state and parameter spaces, we investigate the accuracy and efficiency of both training paradigms. While both paradigms lead to a reasonable approximation of the policy, the model-based approach is more accurate and considerably reduces the number of PDE solves.

97 MATHEMATICS AND COMPUTING↗

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗

Hybrid-RL-MPC4CLR (Hybird-Reinforcement-Learning-Model-Predictive-Control-for-Reserve-Policy-Assisted-Critical-Load-Restoration-in-Distribution-Grids)

Hybrid-RL-MPC4CLR was developed as a hybrid controller for active distribution grid critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. The RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while the MPC models grid operations incorporating the RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. The developers formulated the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The software is developed using various software packages in Python. The MPC's optimal power flow (OPF) model is implemented using the Pyomo package, the RL simulation environment is implemented using the MPC simulation with various scenarios of renewable energy and load demand profiles and power outage beginning times, based on the OpenAI Gym framework. The RL agent training is performed using the RLlib Ray package. The RL algorithm is trained offline using historical forecasts of renewable generation and load demand profiles. Simulation analysis and performance tests are conducted using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery.

Eseye, Abinet Tesfaye↗

Learning Constrained Parametric Differentiable Predictive Control Policies With Guarantees

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.

97 MATHEMATICS AND COMPUTING↗

Gnu-RL: A Precocial Reinforcement Learning Solution for Building HVAC Control Using a Differentiable MPC Policy

Reinforcement learning (RL) was first demonstrated to be a feasible approach to controlling heating, ventilation, and air conditioning (HVAC) systems more than a decade ago. However, there has been limited progress towards a practical and scalable RL solution for HVAC control. While one can train an RL agent in simulation, it is not cost-effective to create a model for each thermal zone or building. Likewise, existing RL agents generally take a long time to learn and are opaque to expert interrogation, making them unattractive for real-world deployment. To tackle these challenges, we propose Gnu-RL: a novel approach that enables practical deployment of RL for HVAC control and re- quires no prior information other than historical data from exist- ing HVAC controllers. To achieve this, Gnu-RL adopts a recently- developed Differentiable Model Predictive Control (MPC) policy, which encodes domain knowledge on planning and system dynam- ics, making it both sample-efficient and interpretable. Prior to any interaction with the environment, a Gnu-RL agent is pre-trained on historical data using imitation learning, which enables it to match the behavior of the existing controller. Once it is put in charge of controlling the environment, the agent continues to improve its policy end-to-end, using a policy gradient algorithm. We evaluate Gnu-RL on both an EnergyPlus model and a real- world testbed. In both experiments, our agents were directly de- ployed in the environment after offline pre-training on expert demonstration. In the simulation experiment, our approach saved 6.6% energy compared to the best published RL result for the same environment, while maintaining a higher level of occupant comfort. Next, Gnu-RL was deployed to control the HVAC of a real-world conference room for a three-week period. Our results show that Gnu-RL saved 16.7% of cooling demand compared to the existing controller and tracked temperature set-point better.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗