Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data- limited”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

The classification of the Arctic Sea ice types and the determination of surface temperature using advanced very high resolution radiometer data

The accurate quantification of new ice and open water areas and surface temperatures within the sea ice packs is a key to the realistic parameterization of heat, moisture, and turbulence fluxes between ocean and atmosphere in the polar regions. Multispectral NOAA advanced very high resolution radiometer/2 (AVHRR/2) satellite images are analyzed to evaluate how effectively the data can be used to characterize sea ice in the Bering and Greenland seas, both in terms of surface type and physical temperature. The basis of the classification algorithm, which is developed using a late wintertime Bering Sea ice cover data, is that frequency distributions of 10.8- micrometers radiances provide four distinct peaks, represeting open water, new ice, young ice, and thick ice with a snow cover. The results are found to be spatially and temporally consistent. Possible sources of ambiguity, especially associated with wider temporal and spatial application of the technique, are discussed. An ice surface temperature algorithm is developed for the same study area by regressing thermal infrared data from 10.8- and 12.0- micrometers channels against station air temperatures, which are assumed to approximate the skin temperatures of adjacent snow and ice. The standard deviations of the results when compared with in situ data are about 0.5 K over leads and polynyas to about 0.5-1.5 K over thick ice. This study is based upon a set of in situ data limited in scope and coverage. Cloud masks are applied using a thresholding technique that utilizes 3.74- and 10.8- micrometers channel data. The temperature maps produced show coherence with surface features like new ice and leads, and consistency with corresponding surface type maps. Further studies are needed to better understand the effects of both the spatial and temporal variability in emissivity, aerosol and precipitable atmospheric ice particle distribution, and atmospheric temperature inversions.

Massom, Robert↗
DOE OSTI2025

Understanding Aitken Mode Aerosol Variability over the Southern Ocean and Antarctica: Insights from Cloud Condensation Nuclei Data

Aitken mode aerosol particles play an important role influencing cloud properties and sustenance, acting as a reservoir of potential cloud condensation nuclei against precipitation scavenging. However, there is limited data on Aitken mode aerosols. In this study, we develop a method to estimate Aitken mode aerosol concentrations and size distribution using cloud condensation nuclei measurements (CCN) and κ-Köhler theory. The performance of this method is evaluated using scanning mobility particle sizer (SMPS) data from recent field campaigns to demonstrate its skills and applicability. The method reasonably estimates Aitken- and accumulation-mode aerosol concentrations, achieving correlations of 0.7–0.9 with only modest biases (mean fractional bias within ±23% for Aitken mode and ±34% for accumulation-mode). This method is further applied to measurements collected over the Southern Ocean and Antarctica in recent years from multiple platforms, including ground sites, aircraft, and ships, to derive Aitken and accumulation-mode aerosol concentrations. Using the derived data, we examine the seasonal cycle, latitudinal variations, and vertical distribution of aerosols. Aitken mode aerosol concentrations are elevated over the Southern Ocean and Antarctica during the austral summer similar to the accumulation mode. In the austral summer, the free troposphere has more Aitken mode aerosols and fewer accumulation mode aerosols than the boundary layer, and thus likely serves as an important source of cloud-forming aerosol while also diluting the accumulation mode.

Kang, Litai [University of Washington] (ORCID:0000↗
NASA NTRS1973

Development of forming and joining technology for TD-NiCr sheet

Forming joining techniques and properties data were developed for thin-gage TD-NiCr sheet in the recrystallized and unrecrystallized conditions. Theoretical and actual forming limit data are presented for several gages of each type of material for five forming processes: brake forming, corrugation forming, joggling, dimpling and beading. Recrystallized sheet can be best formed at room temperature, but unrecrystallized sheet requires forming at elevated temperature. Formability is satisfactory with most processes for the longitudinal orientation but poor for the transverse orientation. Dimpling techniques require further development for both material conditions. Data on joining techniques and joint properties are presented for four joining processes: resistance seam welding (solid-state), resistance spot welding (solid-state), resistance spot welding (fusion) and brazing. Resistance seam welded (solid-state) joints with 5t overlap were stronger than parent material for both material conditions when tested in tensile-shear and stress-rupture. Brazing studies resulted in development of NASA 18 braze alloy (Ni-16Cr-15Mo-8Al-4Si) with several properties superior to baseline TD-6 braze alloy, including lower brazing temperture, reduced reaction with Td-Ni-Cr, and higher stress-rupture properties.

Torgerson, R. T.↗
NASA NTRS1999

Boundary Layer Transition in the NTF: HSR Experience and Plans

Efforts towards understanding boundary layer transition characteristics on a High Speed Civil Transport (HSCT)-class configuration in the National Transonic Facility (NTF) are ongoing. The majority of the High Speed Research (HSR) data base in the NTF has free transition on the wing, even at low Reynolds numbers (Rn) attainable in conventional facilities. Limited data has been obtained and is described herein showing the effects of a conventional, Braslow method based wing boundary-layer trip on drag. Comparisons are made using force data polars and surface flow visualization at selected angles-of-attack and Mach number. Minimum drag data obtained in this study suggest that boundary layer transition occurred very near the wing leading edge by a chord Rn of 30 million. Sublimating chemicals were used in the air mode of operation only at low Rn and low angles-of-attack with no flap deflections; sublimation results suggest that the forebody and outboard wing panel are the only regions with significant laminar flow. The process and issues related to the sublimating chemical technique as applied in the NTF are discussed. Beyond the existing experience, status of efforts to develop a production transition detection system applicable to both air and cryogenic nitrogen environments is presented.

Owens, Lewis R., Jr.↗
NASA NTRS2017

The Epic Chronicle of Designing Cassini's Titan Flyby Altitudes

The selection and optimization of Titan flyby altitudes for NASA's Cassini mission at Saturn has traveled a long, fascinating, and often torturous sixteen-year path - starting in 2001, when pre-arrival trajectory design decisions had to be made, through April of 2017 when Cassini's last, and arguably most critical, low flyby takes place. The chronicle of designing and updating the Titan flyby altitudes have twists and turns enough to satisfy a full-length novel or feature film, including: critical design decision-making before arrival with multiple atmospheric models, high uncertainties, and limited data; early flybys that seemed to show trends that weren't there; use and misuse of statistical analysis; unexpected surprises with limited reaction time; navigation of a scientific, engineering, and management community with a wide array of inherent biases; and consideration of a variety of project risk postures in a high-scrutiny, high-impact, high-reward environment.

Bittner, Molly↗
NASA NTRS2013

Vaporization and Zonal Mixing in Performance Modeling of Advanced LOX-Methane Rockets

Initial modeling of LOX-Methane reaction control (RCE) 100 lbf thrusters and larger, 5500 lbf thrusters with the TDK/VIPER code has shown good agreement with sea-level and altitude test data. However, the vaporization and zonal mixing upstream of the compressible flow stage of the models leveraged empirical trends to match the sea-level data. This was necessary in part because the codes are designed primarily to handle the compressible part of the flow (i.e. contraction through expansion) and in part because there was limited data on the thrusters themselves on which to base a rigorous model. A more rigorous model has been developed which includes detailed vaporization trends based on element type and geometry, radial variations in mixture ratio within each of the "zones" associated with elements and not just between zones of different element types, and, to the extent possible, updated kinetic rates. The Spray Combustion Analysis Program (SCAP) was leveraged to support assumptions in the vaporization trends. Data of both thrusters is revisited and the model maintains a good predictive capability while addressing some of the major limitations of the previous version.

Williams, George J., Jr.↗
DOE OSTI2022

Modeling Electric Vehicle Charging Station Siting Suitability with a Focus on Equity

As adoption of electric vehicles increases, the infrastructure to charge them must keep pace. Determining where to add new charging infrastructure is a complex process subject to many factors, including electrical service availability, vehicle dwell time, the type(s) of drivers and vehicles the stations will serve, traffic levels and timing, and land ownership. In addition, advancing social equity is a current priority of federal efforts to invest in electric vehicle charging infrastructure. Conducting Multi-criteria Decision Analysis (MCDA) within Argonne’s Energy Zones Mapping Tool (EZMT) is a useful method for analyzing many of the factors that influence how suitable a location is for potentially adding new charging infrastructure, and we show how equity metrics can be included in the analysis. However, data limitations impose challenges to using MCDA to evaluate and prioritize locations. We use three examples to demonstrate how to use publicly available data and MDCA to analyze different siting objectives. Each example starts with defining a specific objective and ends with how to use the results to identify specific potential locations that could be investigated further. This analysis demonstrates how interested stakeholders can use the EZMT to run the example MCDA models defined in this study, modify them to suit their needs, or create new MCDA models.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Making a Water Data System Responsive to Information Needs of Decision Makers

Evidence-based environmental management requires data that are sufficient, accessible, useful and used. A mismatch between data, data systems, and data needs for decision making can result in inefficient and inequitable capital investments, resource allocations, environmental protection, hazard mitigation, and quality of life. In this paper, we examine the relationship between data and decision making in environmental management, with a focus on water management. We focus on the concept of decision-driven data systems —data systems that incorporate an assessment of decision-makers' data needs into their design. The aim of the research was to examine the process of translating data into effective decision making by engaging stakeholders in the development of a water data system. Using California's legislative mandate for state agencies to integrate existing water and other environmental data as a case study, we developed and applied a participatory approach to inform data-system design and identify unmet data needs. Using workshops and focused stakeholder meetings, we developed 20 diverse use cases to assess data sources, availability, characteristics, gaps, and other attributes of data used for representative decisions. Federal and state agencies made up about 90% of the data sources, and could readily adapt to a federated data system, our recommended model for the state. The remaining 10% of more-specialized data, central to important decisions across multiple use cases, would require additional investment or incentives to achieve data consistency, interoperability, and compatibility with a federated system. Based on this assessment, we propose a typology of different types of data limitations and gaps described by stakeholders. We also propose technical, governance, and stakeholder engagement evaluation criteria to guide planning and building environmental data systems. Data-system governance involving both producers and users of data was seen as essential to achieving workable standards, stable funding, convenient data availability, resilience to institutional change, and long-term buy-in by stakeholders. Our work provides a replicable lesson for using decision-maker and stakeholder engagement to shape the design of an environmental data system, and inform a technical design that addresses both user and producer needs.

Cantor, Alida↗
DOE OSTI2023

Efficient Reinforcement Learning for Real-Time Hardware-Based Energy System Experiments: Preprint

In the context of urgent climate challenges and the pressing need for rapid technology development, Reinforcement Learning (RL) stands as a compelling data-driven method for controlling real-world physical systems. However, RL implementation often entails time-consuming and computationally intensive data collection and training processes, rendering them inefficient for real-time applications that lack non-real-time models. To address these limitations, real-time emulation techniques have emerged as valuable tools for the lab-scale rapid prototyping of intricate energy systems. While emulated systems offer a bridge between simulation and reality, they too face constraints, hindering comprehensive characterization, testing, and development. In this research, we construct a surrogate model using limited data from simulated systems, enabling an efficient and effective training process for a Double Deep Q-Network (DDQN) agent for future deployment. Our approach is illustrated through a hydropower application, demonstrating the practical impact of our approach on climate-related technology development.

deep Q-learning↗
DOE OSTI2020

Scalable and Actionable Performance Measures for Traffic Signal Systems using Probe Vehicle Trajectory Data

Scalable and actionable performance measures for traffic signal systems provide opportunities for practitioners to measure and improve the transportation network. Historically, traffic signal improvements have relied on scheduled signal retiming based on limited data collection, or on the public to call and alert engineers of an issue. This inefficient method of improving signal timing led to the creation of automated traffic signal performance measures (ATSPMs). These metrics rely on expensive infrastructure, including detection and communications, which has produced barriers for numerous agencies to fully adopt. Recently, third-party data providers have begun to release vehicle trajectory data, which allows for enhanced signal metrics with no investment in physical equipment. The purpose of this study is to demonstrate the use of these data and summarize the scalability of the created metrics. This work builds on previous efforts to quantify signal performance on nine intersections in Michigan, U.S. Ten signalized corridors in Columbus, Ohio, were chosen to scale a performance assessment using crowdsourced trajectory data. A total of 136 intersections were assessed in 2-h intervals using data from all weekdays in 2017. High-level corridor summary metrics including average percent of vehicles stopping (18%–32%), average delay (9.4–20.5 s), and level of travel time reliability (1.23–2.73) were calculated for each corridor direction. Intersection-level metrics were also introduced, which can be used by practitioners to identify problems, improve signal timings, and prioritize future infrastructure investments.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2020

Predicting the propensity for thermally activated β events in metallic glasses via interpretable machine learning

Abstract The elementary excitations in metallic glasses (MGs), i.e., β processes that involve hopping between nearby sub-basins, underlie many unusual properties of the amorphous alloys. A high-efficacy prediction of the propensity for those activated processes from solely the atomic positions, however, has remained a daunting challenge. Recently, employing well-designed site environment descriptors and machine learning (ML), notable progress has been made in predicting the propensity for stress-activated β processes (i.e., shear transformations) from the static structure. However, the complex tensorial stress field and direction-dependent activation could induce non-trivial noises in the data, limiting the accuracy of the structure-property mapping learned. Here, we focus on the thermally activated elementary excitations and generate high-quality data in several Cu-Zr MGs, allowing quantitative mapping of the potential energy landscape. After fingerprinting the atomic environment with short- and medium-range interstice distribution, ML can identify the atoms with strong resistance or high compliance to thermal activation, at a high accuracy over ML models for stress-driven activation events. Interestingly, a quantitative “between-task” transferring test reveals that our learnt model can also generalize to predict the propensity of shear transformation. Our dataset is potentially useful for benchmarking future ML models on structure-property relationships in MGs.

36 MATERIALS SCIENCE↗
NASA NTRS2007

Analysis of Chromosomal Aberrations in the Blood Lymphocytes of Astronauts after Space Flight

It is a NASA requirement that biodosimetry analysis be performed on all US astronauts who participate in long duration missions of 3 months or more onboard the International Space Station. Cytogenetic analysis of blood lymphocytes is the most sensitive and reliable biodosimetry method available at present, especially if chromosome damage is assessed before as well as after space flight. Results provide a direct measurement of space radiation damage in vivo that takes into account individual radiosensitivity and considers the influence of microgravity and other stress conditions. We present data obtained from all twenty-five of the crewmembers who have participated in the biodosimetry program so far. The yield of chromosome exchanges, measured using fluorescence in situ hybridization (FISH) technique with chromosome painting probes, increased after space flight for all these individuals. In vivo dose was derived from frequencies of chromosome exchanges using preflight calibration curves of in vitro exposed cells from the same individual, and RBE was compared with individually measured physically absorbed dose and projected organ dose equivalents. Biodosimetry estimates using samples collected within a few weeks of return from space lie within the range expected from physical dosimetry. For some of these individuals chromosome aberrations were assessed again several months after their respective missions and a temporal decline in stable exchanges was observed in some cases, suggesting that translocations are unstable with time after whole body exposure to space radiation. This may indicate complications with the use of translocations for retrospective dose reconstruction. Data from one crewmember who has participated in two separate long duration space missions and has been followed up for over 10 years provides limited data on the effect of repeat flights and shows a possible adaptive response to space radiation exposure.

George, K.↗
DOE OSTI2020

Predicting Small Molecule Transfer Free Energies by Combining Molecular Dynamics Simulations and Deep Learning

Accurately predicting small molecule partitioning and hydrophobicity is critical in the drug discovery process. There are many heterogeneous chemical environments within a cell and entire human body. For example, drugs must be able to cross the hydrophobic cellular membrane to reach their intracellular targets, and hydrophobicity is an important driving force for drug–protein binding. Atomistic molecular dynamics (MD) simulations are routinely used to calculate free energies of small molecules binding to proteins, crossing lipid membranes, and solvation but are computationally expensive. Machine learning (ML) and empirical methods are also used throughout drug discovery but rely on experimental data, limiting the domain of applicability. We present atomistic MD simulations calculating 15,000 small molecule free energies of transfer from water to cyclohexane. This large data set is used to train ML models that predict the free energies of transfer. We show that a spatial graph neural network model achieves the highest accuracy, followed closely by a 3D-convolutional neural network, and shallow learning based on the chemical fingerprint is significantly less accurate. A mean absolute error of ~4 kJ/mol compared to the MD calculations was achieved for our best ML model. We also show that including data from the MD simulation improves the predictions, tests the transferability of each model to a diverse set of molecules, and show multitask learning improves the predictions. This work provides insight into the hydrophobicity of small molecules and ML cheminformatics modeling, and our data set will be useful for designing and testing future ML cheminformatics methods.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2008

Space Radiation Induced Cytogenetic Damage in the Blood Lymphocytes of Astronauts

Cytogenetic analysis of astronauts blood lymphocytes provides a direct in vivo measurement of space radiation damage, which takes into account individual radiosensitivity and considers the influence of microgravity and other stress conditions. We present our latest analyses of chromosome damage in astronauts blood lymphocytes assessed by fluorescence in situ hybridization (FISH) chromosome painting and collected at various times beginning directly after return from space to several years after flight. Dose was derived from frequencies of chromosome exchanges using preflight calibration curves, and the Relative Biological Effect (RBE) was estimated by comparison with individually measured physically absorbed doses. Values for average RBE were compared to the average quality factor (Q), from direct measurements of the lineal energy spectra using a tissue-equivalent proportional counter (TEPC) and radiation transport codes. Results prove that cytogenetic biodosimetry analyses on blood collected within a week or two of return from space provides a reliable estimate of equivalent radiation dose and risk after protracted exposure to space radiation of a few months or more. However, data collected several months or years after flight suggests that the yield of chromosome translocations may decline with time after the mission, indicating that retrospective doses may be more difficult to estimate. In addition, limited data on multiple flights show a lack of correlation between time in space and translocation yields. Data from one crewmember, who has participated in two separate long-duration space missions and has been followed up for over 10 years, provide limited information on the effect of repeat flights and show a possible adaptive response to space radiation exposure.

George, K.↗
DOE OSTI2025

Reevaluation of Radiation-Protection Standards for Workers and the Public Based on Current Scientific Evidence

President Trump’s recent executive orders to “Usher in a Nuclear Renaissance,” coupled with the global pledge to triple nuclear energy capacity by 2050, underscore nuclear energy’s importance to national security and economic prosperity. This renewed interest has prompted efforts to spur nuclear-energy deployment, including assessing factors impeding it. One issue that has previously been identified as adding to the cost of nuclear energy is excessively conservative requirements, including those related to radiation protection. This technical review, therefore, examines current radiation-protection standards that were established decades ago when more limited data were available and nuclear-energy expansion was not a national priority. The review focuses on scientific evidence regarding the health effects of ionizing radiation at annual doses of 10,000 mrem or less. The review evaluates epidemiological studies, radiobiological research, and positions of relevant professional organizations to assess whether such doses result in discernable or observable increases in negative health outcomes. The review also surveys the literature related to economic and practical implications of current radiation-protection standards and practices. Based on this assessment, we propose maintaining an annual occupational whole-body dose limit of 5,000 mrem/yr and eliminating all “as low as reasonably achievable” requirements and limits below this threshold. This change could potentially reduce radiation-protection costs by millions of dollars annually for each reactor, as well as decrease the overall costs and correct misconceptions about the risks associated with all nuclear technologies. The evidence further supports future consideration of a 10,000 mrem/yr limit that would maintain appropriate safety margins while further reducing protection costs. Similarly, given the data and that the average annual radiation dose per person in the U.S. is 620 mrem, we believe the public dose limits of 100 mrem/yr are unnecessarily restrictive; increasing to 500 mrem/yr would maintain substantial safety margins—a factor of 10 below the occupational limit—while reducing regulatory burdens and associated bureaucracy. While we acknowledge ongoing scientific debate and encourage continued research on the health effects of ionizing radiation, our review indicates current frameworks are overly conservative. These overly stringent limits not only impose unnecessary economic burdens without corresponding health benefits but also divert safety focus and resources from more important considerations. Although this study was motivated by nuclear-power considerations, reforms to radiation-protection requirements have significant positive implications for other areas, such as nuclear medical applications, environmental remediation, nuclear-waste management and disposal, and industrial applications of nuclear technologies.

61 RADIATION PROTECTION AND DOSIMETRY↗
NASA NTRS1984

The reflection of airborne UV laser pulses from the ocean

It is experimentally shown here for the first time that the normalized laser backscatter cross-section of the sea surface is a function of elevation or height position on teh ocean wave. All data were taken off-nadir, resulting in incidence angles of about 6.5 deg measured relative to the normal to mean sea level (MSL). In the limited data sets analyzed to date, the normalized backscatter cross-section was found to be higher in wave crest regions and lower in wave troughs for a swell-dominated sea over which the wind speed was 5 m/s. The reverse was found to be the case for a sea that was driven by a 14 m/s wind. These isolated results show that the MSL, as measured by an off-nadir and/or multibeam type satellite laser altimeter, will be found above, at, or below the true MSL, depending on the local sea conditions existing in the footprint of the altimeter. Airborne nadir-pointed laser altimeter data for a wide variety of sea conditions are needed before a final determination can be made of the effect of sea state on the backscatter cross-section as measured by a down-looking satellite laser system.

Hoge, F. E.↗
NASA NTRS2002

A Miniature Mineralogical Instrument for In-Situ Characterization of Ices and Hydrous Minerals at the Lunar Poles

Lunar missions over the past few years have provided new evidence that water may be present at the lunar poles in the form of cold-trapped ice deposits, thereby rekindling interest in sampling the polar regions. Robotic landers fitted with mineralogical instrumentation for in-situ analyses could provide unequivocal answers on the presence of crystalline water ice and/or hydrous minerals at the lunar poles. Data from Lunar Prospector suggest that any surface exploration of the lunar poles should include the capability to drill to depths of more than 40 cm. Limited data on the lunar geotherm indicate temperatures of approximately 245-255 K at regolith depths of 40 cm, within a range where water may exist in the liquid state as brine. A relevant terrestrial analog occurs in Antarctica, where the zeolite mineral chabazite has been found at the boundary between ice-free and ice-cemented regolith horizons, and precipitation from a regolith brine is indicated. Soluble halogens and sulfur in the lunar regolith could provide comparable brine chemistry in an analogous setting. Regolith samples collected by a drilling device could be readily analyzed by CheMin, a mineralogical instrument that combines X-ray diffraction (XRD) and X-ray fluorescence (XRF) techniques to simultaneously characterize the chemical and mineralogical compositions of granular or powdered samples. CheMin can unambiguously determine not only the presence of hydrous alteration phases such as clays or zeolites, but it can also identify the structural variants or types of clay or zeolite present (e.g., well-ordered versus poorly ordered smectite; chabazite versus phillipsite). In addition, CheMin can readily measure the abundances of key elements that may occur in lunar minerals (Na, Mg, Al, Si, K, Ca, Fe) as well as the likely constituents of lunar brines (F, Cl, S). Finally, if coring and analysis are done during the lunar night or in permanent shadow, CheMin can provide information on the chemistry and structure of any crystalline ices that might occur in the regolith samples.

Sarrazin, P.↗
DOE OSTI2023

Correlated Trajectory Uncertainty for Adaptive Sequential Decision Making

One of the great challenges with decision making tasks on real world systems is the fact that data is sparse and acquiring additional data is expensive. In these cases, it is often crucial to make a model of the environment to assist in making decisions. At the same time, limited data means that learned models are erroneous, making it just as important to equip the model with good predictive uncertainties. In the context of learning sequential decision making policies, these uncertainties can prove useful for informing which data to collect for the greatest improvement in policy performance \citep{mehta2021experimental, mehta2022exploration} or informing the policy about unsure regions of state and action space to avoid during test time \citep{yu2020mopo}. Additionally, assuming that realistic samples of the environment can be drawn, an adaptable policy can be trained that attempts to make optimal decisions for any given possible instance of the environment \citep{ghosh2022offline, chen2021offline}. In this work, we examine the so-called ``probabilistic neural network'' (PNN) model that is ubiquitous in model-based reinforcement learning (MBRL) works. We argue that while PNN models may have good marginal uncertainties, they form a distribution of non-smooth transition functions. Not only are these samples unrealistic and may hamper adaptability, but we also assert that this leads to poor uncertainty estimates when predicting multiple step trajectory estimates. To address this issue, we propose a simple sampling method that can be implemented on top of pre-existing models.We evaluate our sampling technique on a number of environments, including a realistic nuclear fusion task, and find that, not only do smooth transition function samples produce more calibrated uncertainties, but they also lead to better downstream performance for an adaptive policy.

Offline Reinforcement Learning↗