Results 31 to 40 of about 2,271,128 (293)

Safe Exploration in Markov Decision Processes

CoRR, 2012
In environments with uncertain dynamics exploration is necessary to learn how to perform well. Existing reinforcement learning algorithms provide strong exploration guarantees, but they tend to rely on an ergodicity assumption. The essence of ergodicity is that any state is eventually reachable from any other state by following a suitable policy.
Teodor Mihai Moldovan, Pieter Abbeel
openaire   +3 more sources

Towards Human-Level Safe Reinforcement Learning in Atari Library

Jurnal Sisfokom, 2023
Reinforcement learning (RL) is a powerful tool for training agents to perform complex tasks. However, from time-to-time RL agents often learn to behave in unsafe or unintended ways.
Afriyadi Afriyadi, Wiranto Herry Utomo
doaj   +1 more source

Information-Theoretic Safe Exploration with Gaussian Processes

Advances in Neural Information Processing Systems 35, 2022
Submitted to NeurIPS ...
Alessandro G. Bottero, Carlos E. Luis, Julia Vinogradska, Felix Berkenkamp, Jan Peters 0001   +4 more
openaire   +4 more sources

Element geochemical characteristics of Mesozoic mudstones in the northern piedmont zone of the Kuqa depression and their implications to sedimentary environments

矿业科学学报, 2019
By means of element geochemistry, the characteristics of major elements, trace elements and rare earth elements (REE) for Triassic and Jurassic mudstones from the northern piedmont zone in the Kuqa depression were studied and discussed for the ...
Liang Wanle, Li Xianqing, Wei Qiang, Li Jin, Sun Kexin, He Yukai, Zhang Yachao   +6 more
doaj   +1 more source

Kansas Safe Kids Annual Report

, 2023
Safe Kids Kansas is a 501c(3) charitable organization and is a member of Safe Kids Worldwide, a global organization dedicated to preventing injuries in children.
Safe Kids Kansas, Inc.
core   +1 more source

Kansas Safe Kids Annual Report

, 2021
Safe Kids Kansas is a 501c(3) charitable organization and is a member of Safe Kids Worldwide, a global organization dedicated to preventing injuries in children.
Safe Kids Kansas, Inc.
core   +1 more source

Compositions, Sources, and Aging Processes of Aerosol Particles during Winter Hazes in an Inland Megacity of NW China

Atmosphere, 2022
As one of the largest inland megacities in Northwest (NW) China, Xi’an has been facing serious regional haze frequently, especially during winter. The composition of aerosols in Xi’an is highly complex due to its unique basinal topography and unique ...
Pengju Liu, Longyi Shao, Yaowei Li, Wenhua Wang, Mengyuan Zhang, Cheng-Xue Yang, Hongya Niu, Xiaolei Feng, Daizhou Zhang   +8 more
doaj   +1 more source

Safe Exploration for Interactive Machine Learning

CoRR, 2019
In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions.
Matteo Turchetta, Felix Berkenkamp, Andreas Krause 0001   +2 more
openaire   +4 more sources

Volcanically-Induced Environmental and Floral Changes Across the Triassic-Jurassic (T-J) Transition

Frontiers in Ecology and Evolution, 2022
The End-Triassic Mass Extinction (ETME) saw the catastrophic loss of ca. 50% of marine genera temporally associated with emplacement of the Central Atlantic Magmatic Province (CAMP).
Peixin Zhang, Jing Lu, Minfang Yang, David P. G. Bond, Sarah E. Greene, Le Liu, Yuanfu Zhang, Ye Wang, Ziwei Wang, Shan Li, Longyi Shao, Jason Hilton   +11 more
doaj   +1 more source

Deep Reinforcement Learning Task Assignment Based on Domain Knowledge

IEEE Access, 2022
Deep Reinforcement Learning (DRL) methods are inefficient in the initial strategy exploration process due to the huge state space and action space in large-scale complex scenarios.
Jiayi Liu, Gang Wang, Xiangke Guo, Siyuan Wang, Qiang Fu   +4 more
doaj   +1 more source