Results 11 to 20 of about 2,271,128 (293)

Safe- to-Explore State Spaces: Ensuring Safe Exploration in Policy Search with Hierarchical Task Optimization [PDF]

open access: yes2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018
In 2018 IEEE-RAS International Conference on Humanoid Robots (Humanoids), Beijing ...
Jens Lundell   +4 more
openaire   +5 more sources

Safe Exploration for Optimizing Contextual Bandits [PDF]

open access: yesACM Transactions on Information Systems, 2020
Contextual bandit problems are a natural fit for many information retrieval tasks, such as learning to rank, text classification, recommendation, and so on. However, existing learning methods for contextual bandit problems have one of two drawbacks: They either do not explore the space of all possible document rankings (i.e., actions) and, thus, may ...
Rolf Jagerman   +2 more
openaire   +6 more sources

Safe Visual Data Exploration [PDF]

open access: yesProceedings of the 2017 ACM International Conference on Management of Data, 2017
Exploring data via visualization has become a popular way to understand complex data. Features or patterns in visualization can be perceived as relevant insights by users, even though they may actually arise from random noise. Moreover, interactive data exploration and visualization recommendation tools can examine a large number of observations, and ...
Zheguang Zhao   +5 more
openaire   +2 more sources

Reinforcement Learning by Guided Safe Exploration [PDF]

open access: yes, 2023
Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment.
Qisong Yang   +4 more
openaire   +3 more sources

A simultaneous determination method for diamondoids and thiadiamondoids in condensate oil and its geological significance: taking condensate oil from central Tarim Basin as an example

open access: yesShiyou shiyan dizhi, 2021
Diamondoids and thiadiamondoids in crude oil samples have the similar diamond-like cage structures, which can reflect the thermal cracking and thermochemical sulfate reduction(TSR) effect during geological processes.
Chenchen FANG   +3 more
doaj   +1 more source

Reservoir Characteristics of Tight Sandstone and Sweet Spot Prediction of Dibei Gas Field in Eastern Kuqa Depression, Northwest China

open access: yesEnergies, 2022
Great progress has been made in the exploration of tight sandstone gas resources in Kuqa depression. Great progress has been made in Dibei structural belt, which proves the previously unproven favorable area for tight sandstone gas.
Guangjie Zhao   +5 more
doaj   +1 more source

Study on the Rheology of CO2 Hydrate Slurry by Using the Capillary Method

open access: yesJournal of Marine Science and Engineering, 2022
The rheological properties of the CO2 hydrate slurry are experimentally investigated by using a new flow loop with an inner diameter of 50 mm. The pressure drops of the CO2 hydrate slurry are measured experimentally under the volumetric hydrate fraction,
Weiqi Fu   +4 more
doaj   +1 more source

Guiding Safe Exploration with Weakest Preconditions

open access: yesCoRR, 2022
In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training. We present a novel neurosymbolic approach called SPICE to solve this safe exploration problem.
Greg Anderson 0003   +2 more
openaire   +3 more sources

GC×GC-TOFMS analysis of ethanodiamondoids in Ordovician oil from well SN1, Tarim Basin

open access: yesShiyou shiyan dizhi, 2023
By 2D gas chromatography and time-of-flight mass spectrometry (GC×GC-TOFMS), 81 ethanodiamondoids with 1-3 cages were detected quantitatively in Ordovician crude oil from well SN1, Shuntuoguole area, Tarim Basin, including 47 ethanoadamantanes with total
Xiao YU   +4 more
doaj   +1 more source

Benefits of Monotonicity in Safe Exploration with Gaussian Processes

open access: yesCoRR, 2022
We consider the problem of sequentially maximising an unknown function over a set of actions while ensuring that every sampled point has a function value below a given safety threshold. We model the function using kernel-based and Gaussian process methods, while differing from previous works in our assumption that the function is monotonically ...
Arpan Losalka, Jonathan Scarlett
openaire   +4 more sources

Home - About - Disclaimer - Privacy