Search NASA⌕ Search

SEARCH · Search NASA

Results for “Policy optimization”

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.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

How good are learning-based control v.s. model-based control for load shifting? Investigations on a single zone building energy system

Both model predictive control (MPC) and deep reinforcement learning control (DRL) have been presented as a way to approximate the true optimality of a dynamic programming problem, and these two have shown significant operational cost saving potentials for building energy systems. Furthermore, there is still a lack of in-depth quantitative studies on their approximation levels to the true optimality, especially in the building energy domain. To fill in the gap, this paper provides a numerical framework that enables the evaluation of the optimality levels of different controllers for building energy systems. This framework is then used to comprehensively compare the optimal control performance of both MPC and DRL controllers with given computation budgets for a single zone fan coil unit system. Note the optimality is estimated based on a user-specific selection of trade-off weights among energy costs, thermal comfort and control slew rates. Compared with the best optimality we can find through expensive optimization simulations, the best DRL agent can maximally approximate the optimality by 96.54%, which outperforms the best MPC whose optimality level is 90.11%. However, due to the stochasticity, the DRL agent is only expected to approximate the optimality by 90.42%, which is almost equivalent to the best MPC. Except for Proximal Policy Optimization (PPO), all DRL agents can have a better approximation to the optimality than the best MPC, and are expected to have better approximation than the MPC with a prediction horizon of 32 steps (15 min per step). In terms of reducing energy cost and thermal discomfort, MPC can outperform the rule-based control (RBC) by 18.47%–25.44%. DRL can be expected to outperform RBC by 18.95%–25.65% ,and the best DRL control policy can outperform RBC by 20.29%–29.72%. Although the comparison of the optimality level is performed in a perfect setting, e.g., MPC assumes perfect models, and DRL assumes a perfect offline training process and online deployment process, this can shed insight on their capabilities of approximating to the original dynamic programming problem.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Variational actor-critic algorithms,

We introduce a class of variational actor-critic algorithms based on a variational formulation over both the value function and the policy. The objective function of the variational formulation consists of two parts: one for maximizing the value function and the other for minimizing the Bellman residual. Besides the vanilla gradient descent with both the value function and the policy updates, we propose two variants, the clipping method and the flipping method, in order to speed up the convergence. We also prove that, when the prefactor of the Bellman residual is sufficiently large, the fixed point of the algorithm is close to the optimal policy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

K-Spin Hamiltonian for Quantum-Resolvable Markov Decision Processes

The Markov decision process is the mathematical formalization underlying the modern field of reinforcement learning when transition and reward functions are unknown. We derive a pseudo-Boolean cost function that is equivalent to a K-spin Hamiltonian representation of the discrete, finite, discounted Markov decision process with infinite horizon. This K-spin Hamiltonian furnishes a starting point from which to solve for an optimal policy using heuristic quantum algorithms such as adiabatic quantum annealing and the quantum approximate optimization algorithm on near-term quantum hardware. In arguing that the variational minimization of our Hamiltonian is approximately equivalent to the Bellman optimality condition for a prevalent class of environments we establish an interesting analogy with classical field theory. Along with proof-of-concept calculations to corroborate our formulation by simulated and quantum annealing against classical Q-Learning, we analyze the scaling of physical resources required to solve our Hamiltonian on quantum hardware.

Hamiltonian↗
DOE OSTI2025

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with genetic algorithms to address these limitations. Our approach optimizes multiple user-specified properties including quantitative estimates of drug-likeness (QED), synthetic accessibility (SA), and ADMET (absorption, distribution, metabolism, excretion, and toxicity) endpoints without requiring complete model retraining, while maintaining capability for scaffold-constrained generation where specific substructures must be preserved. We outperform state-of-the-art methods for molecular optimization, achieving best QED scores across GDB13, Moses, and Zinc datasets with up to 31% improvement over previous methods while maintaining excellent validity, uniqueness, and novelty metrics. For simultaneous multi-property optimization, our framework achieves substantial improvements in ADMET properties including 4.5-fold reduction in hERG toxicity and enhanced Caco-2 permeability compared to Moses dataset. Under structural constraints, the framework significantly improves molecular validity while preserving scaffolds and effectively optimizing properties. In conclusion, this versatile solution advances pharmaceutical and materials molecular design through effective integration of reinforcement learning and genetic algorithms with multi-property optimization and scaffold preservation.

Genetic algorithms↗
DOE OSTI2022

The Policy Mullet: Good Intentions in the Front, Bad Policy in the Back

To achieve important policy goals like decarbonization, energy efficiency, and social justice, it is important to translate high-level policy into operational practice. Establishing sustainable purchasing goals has been one important part of this translation. However, not all sustainable purchasing policies are equally effective for organizations. In this study, we analyze sustainable purchasing policies collected from 30 public-sector organizations. We discuss a theoretical framework of optimal policy language and use that framework to evaluate the policies we collected. We believe that an ideal sustainable purchasing policy can increase the likelihood of implementation success by providing more product-specific guidance, giving authority to procurement staff, setting performance targets, and requiring reporting to account for progress. In our review of public sector sustainable purchasing policies, we found that policy language is less than ideal when measured against the framework. Based on our findings, we highlight the best practice language organizations can use in their sustainable purchasing policies to meet sustainability goals. While there is more work needed to inform best practices with sustainable purchasing policies, we recommend that organizations utilize existing frameworks when developing a sustainable purchasing policy to encourage better implementation.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2015

Optimal carbon capture and storage contracts using historical CO 2 emissions levels

In an effort to reduce carbon dioxide (CO 2 ) emissions to the atmosphere, carbon capture and storage (CCS) technology has been developed to collect CO 2 from emissions generators and store it underground. Recent proposed legislation would limit the volume of emissions generated from power sources, effectively requiring some sources to participate in CCS. Both emissions sources and storage operators require incentives to enter into contracts to capture excess emissions at the source, and transport and store the CO 2 underground. As the level of emissions from power plants is stochastic and carryover into future time periods is expensive, we develop a newsvendor model to determine the optimal price and volume of these contracts to maximize the expected profit of the storage operator and encourage the participation of multiple emissions sources. Because the storage operator has a limit on the amount of CO 2 that can be injected each month, this limit affects the allocation of the optimal contract amounts between the emitters. Furthermore, the distribution of emissions and relative costs of transportation also influence the optimal policy. In addition to analytical solutions, we present data-driven methods for using correlated emissions data to determine the optimal price and volume of these contracts.

42 ENGINEERING↗
DOE OSTI2025

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Design and optimization of a modular hydrogen-based integrated energy system to maximize revenue via nuclear-renewable sources

Here, this paper demonstrates a novel modular distributed framework that uses optimal energy-dispatching strategies to enable greater flexibility and profitability in nuclear-renewable integrated energy systems (NR-IES). Hydrogen is used as a commodity in this framework since its production can improve grid stability and system operational flexibility, decarbonize heavy industry, and create an additional revenue stream for electricity generators, particularly nuclear power plants with high operational expenses. The proposed solution addresses the challenges associated with merging multiple software and services from various domains by using functional mock-up units (FMU) to co-simulate diverse subsystems designed in various platforms. The tightly coupled integrated energy system (IES) is optimized to maximize revenue by utilizing the deep reinforcement learning (DRL) technique to make smart dispatching decisions based on variable electricity prices and the availability of renewable energy. Proximal policy optimization (PPO) algorithm is used in training and testing the DRL agent. Over a period of 120 days, the proposed hydrogen-based IES framework showed about 10% revenue boost compared to a non-hydrogen generating baseline IES while also providing an easily-adoptable framework which can help to improve the flexibility of future generation nuclear power plants.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Soft Actor Critic Based Volt-VAR Co-optimization in Active Distribution Grids

Modern distribution networks are undergoing several technical challenges, such as voltage fluctuations, because of high penetration of distributed energy resources (DERs). This paper proposes a deep reinforcement learning (DRL)-based Volt VAR co-optimization technique for reducing voltage fluctuations as well as power loss under high penetration of DERs. In addition, the proposed approach minimizes the operational cost of the grid. A stochastic policy optimization based soft actor critic (SAC) agent is proposed to configure the optimal set-points of the reactive power outputs of the inverters. The performance of the proposed model is verified on the modified IEEE 34- and 123-bus systems and compared with a base case scenario with no reactive supply by inverters, and a local droop control approach. The results demonstrate that the proposed framework outperforms the conventional droop control method in improving the voltage profile, minimizing the network power loss, and reducing grid operational cost.

—Distribution grids, deep reinforcement learning, ↗
DOE OSTI2020

Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV Based Random Access IoT Networks With NOMA

In this paper, we apply the Non-Orthogonal Multiple Access (NOMA) technique to improve the massive channel access of a wireless IoT network where solar-powered Unmanned Aerial Vehicles (UAVs) relay data from IoT devices to remote servers. Specifically, IoT devices contend for accessing the shared wireless channel using an adaptive p-persistent slotted Aloha protocol; and the solar-powered UAVs adopt Successive Interference Cancellation (SIC) to decode multiple received data from IoT devices to improve access efficiency. To enable an energy-sustainable capacity-optimal network, we study the joint problem of dynamic multi-UAV altitude control and multi-cell wireless channel access management of IoT devices as a stochastic control problem with multiple energy constraints. We first formulate this problem as a Constrained Markov Decision Process (CMDP), and propose an online model-free Constrained Deep Reinforcement Learning (CDRL) algorithm based on Lagrangian primal-dual policy optimization to solve the CMDP. Extensive simulations demonstrate that our proposed algorithm learns a cooperative policy in which the altitude of UAVs and channel access probability of IoT devices are dynamically controlled to attain the maximal long-term network capacity while ensuring energy sustainability of UAVs, outperforming baseline schemes. The proposed CDRL agent can be trained on a small network, yet the learned policy can efficiently manage networks with a massive number of IoT devices and varying initial states, which can amortize the cost of training the CDRL agent.

42 ENGINEERING↗
DOE OSTI2022

PWR loading pattern optimization with reinforcement learning

The core loading pattern optimization problem belongs to the class of combinatorial optimization problem and has been studied since the dawn of commercial nuclear energy industry. It is characterized by multiple objectives and constraints, with a very high number of candidate patterns, which makes it impossible to solve explicitly. Stochastic optimization methodologies including Genetic Algorithms and Simulated Annealing are used by different nuclear utilities and vendors to perform fuel cycle reload design. Nevertheless, hand-designed solutions continue to be the prevalent method in the industry. To improve the state-of-the-art core reload patterns, we aim to create a method as scalable as possible, that agrees with the designer's goal of performance and safety. To help in this task Deep Reinforcement Learning (DRL), in particular Proximal Policy Optimization is leveraged. DRL has recently experienced a strong impetus from its successes applied to games, sometimes even reaching 'super-human' performances. This paper lays out the foundation of this method and proposes to study the behavior of several hyper-parameters that influence the DRL algorithm. The algorithm is highly dependent on multiple factors such as an exploration/exploitation trade-off that manifests through different parameters such as the number of loading patterns seen and the number of samples collected before a policy update, but also the shape of the objective function derived for the core design. Experimental results also demonstrate the effectiveness of the method in finding high-quality solutions from scratch within a reasonable amount of time. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Deep reinforcement learning based optimization for a tightly coupled nuclear renewable integrated energy system

New ways to integrate energy systems to maximize efficiency are being sought to meet carbon emissions goals. Nuclear-renewable integrated energy system (NR-IES) concepts are a leading solution that couples a nuclear power plant with renewable energy, hydrogen generation plants, and energy storage systems, such that thermal and electrical power are dispatchable to fulfill grid-flexibility requirements while also producing hydrogen and maximizing revenue. Here, this paper introduces a deep reinforcement learning (DRL)-based framework to address the complex decision-making tasks for NR-IES. The objective is to maximize revenue by generating and selling hydrogen and electricity simultaneously according to their time-varying prices while keeping the energy flow in the subsystems in balance. A Python-based simulator for a NR-IES concept has been developed to integrate with OpenAI Gym and Ray/RLlib to enable an efficient and flexible computational framework for DRL research and development. Three state-of-the-art DRL algorithms have been investigated, including two-delayed deep deterministic policy gradient (TD3), soft-actor critic (SAC), proximal policy optimization (PPO), to illustrate DRL’s superiority for controlling NR-IES by comparing it with a conventional control approach, particle swarm optimization (PSO). In this effort, PPO has shown more-stable performance and also better generalization capability than SAC and TD3. Comparisons with PSO have demonstrated that, on average, PPO can achieve 13.9% more mean episode returns from the training process and 29.4% more mean episode returns from the testing process when different hydrogen-production targets are applied.

08 HYDROGEN↗
DOE OSTI2021

Distributionally Robust Partially Observable Markov Decision Process with Moment-Based Ambiguity

In this paper, we consider a distributionally robust partially observable Markov decision process (DR-POMDP), where the distribution of the transition-observation probabilities is unknown at the beginning of each decision period, but their realizations can be inferred using side information at the end of each period after an action being taken. We build an ambiguity set of the joint distribution using bounded moments via conic constraints and seek an optimal policy to maximize the worst-case (minimum) reward for any distribution in the set. We show that the value function of DR-POMDP is piecewise linear convex with respect to the belief state and propose a heuristic search value iteration method for obtaining lower and upper bounds of the value function. We conduct numerical studies and demonstrate the computational performance of our approach via testing instances of a dynamic epidemic control problem. Our results show that DR-POMDP can produce more robust policies under misspecified distributions of transition-observation probabilities as compared to POMDP but has less costly solutions than robust POMDP. The DR-POMDP policies are also insensitive to varying parameter in the ambiguity set and to noise added to the true transition-observation probability values obtained at the end of each decision period.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Bridging Control and Deployment: A Cross-Layer Analysis of Scalable Building Cluster Control

Building cluster control has emerged as a promising approach for enabling flexible and coordinated operation of distributed building systems, yet its transition from pilot demonstrations to routine grid-interactive operation remains limited. This paper argues that this gap cannot be explained by control algorithms alone. Instead, it arises from interacting barriers in communication infrastructure, data and semantic interoperability, uncertainty management, stakeholder participation, market design, and policy support. Accordingly, the paper reviews both technical and non-technical barriers to building cluster control. Technical challenges include heterogeneous devices and protocols, communication latency and reliability, distributed decision-making, and uncertainty propagation across aggregated loads. Non-technical barriers include user participation, stakeholder coordination, incentive allocation, and data governance. Existing solution approaches are synthesized, including semantic interoperability frameworks, edge and hierarchical communication architectures, distributed and transactive control strategies, uncertainty-aware optimization, policy mechanisms, and market reforms. Based on this analysis, two research directions are identified: testing infrastructures that can evaluate control performance under realistic multi-building conditions, and abstraction methods that allow building clusters to interact with other energy sectors through standardized flexibility representations. Overall, the paper provides a structured review of how building cluster control can move from isolated demonstrations toward reproducible, market-compatible, and grid-relevant implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems: Preprint

We present the PowerGridworld software package to provide users with a light-weight, modular, and customizable framework for creating power systems-focused, multi-agent gym environments that readily integrate with existing training frameworks for reinforcement learning (RL). While many frameworks exist for training multi-agent (MA) RL policies, none exist to rapidly prototype and develop the environments themselves, especially in the context of heterogeneous (composite, multi-device) power systems where power flow solutions are required to define grid-level variables and costs. PowerGridworld is an open-source software package that helps to fill this gap. To highlight PowerGridworld's key features, we present two case studies and demonstrate learning multi-agent RL policies using both OpenAI's MADDPG and RLLib's PPO algorithms where, in both cases, at least some subset of agents incorporate elements of the power flow solution at each time step as part of their reward (negative cost) structures.

MATHEMATICS AND COMPUTING↗
DOE OSTI2023

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↗
DOE OSTI2017

Continuous-Time Public Good Contribution Under Uncertainty: A Stochastic Control Approach

In this paper we study continuous-time stochastic control problems with both monotone and classical controls motivated by the so-called public good contribution problem. That is the problem of n economic agents aiming to maximize their expected utility allocating initial wealth over a given time period between private consumption and irreversible contributions to increase the level of some public good. We investigate the corresponding social planner problem and the case of strategic interaction between the agents, i.e. the public good contribution game. We show existence and uniqueness of the social planner’s optimal policy, we characterize it by necessary and sufficient stochastic Kuhn–Tucker conditions and we provide its expression in terms of the unique optional solution of a stochastic backward equation. Similar stochastic first order conditions prove to be very useful for studying any Nash equilibria of the public good contribution game. In the symmetric case they allow us to prove (qualitative) uniqueness of the Nash equilibrium, which we again construct as the unique optional solution of a stochastic backward equation. We finally also provide a detailed analysis of the so-called free rider effect.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗