Safe reinforcement learning - Open Access .click

Results 41 to 50 of about 7,404,725 (288)

A Survey of Text Games for Reinforcement Learning Informed by Natural Language

Transactions of the Association for Computational Linguistics, 2022
Reinforcement Learning has shown success in a number of complex virtual environments. However, many challenges still exist towards solving problems with natural language as a core component.
Philip Osborne, Heido Nõmm, André Freitas +2 more
doaj +1 more source

Gut microbiome and aging—A dynamic interplay of microbes, metabolites, and the immune system

FEBS Letters, EarlyView.
Age‐dependent shifts in microbial communities engender shifts in microbial metabolite profiles. These in turn drive shifts in barrier surface permeability of the gut and brain and induce immune activation. When paired with preexisting age‐related chronic inflammation this increases the risk of neuroinflammation and neurodegenerative diseases.
Aaron Mehl, Eran Blacher
wiley +1 more source

Shields for Safe Reinforcement Learning

Communications of the ACM
Reinforcement learning (RL) is a prominent machine learning technique used to optimize an agent’s performance in potentially unknown environments. Despite its popularity and success, RL lacks safety guarantees, both during the learning phase and deployment.
Bettina Könighofer +4 more
openaire +4 more sources

Routing Using Safe Reinforcement Learning. [PDF]

, 2020
The ever increasing number of connected devices has lead to a metoric rise in the amount data to be processed. This has caused computation to be moved to the edge of the cloud increasing the importance of efficiency in the whole of cloud. The use of this fog computing for time-critical control applications is on the rise and requires robust guarantees ...
Gautham Nayak Seetanadi, Karl-Erik Årzén +1 more
openaire +3 more sources

Safe Reinforcement Learning in a Simulated Robotic Arm

, 2023
4 pages, 2 figures. Appeared in 2023 International Conference on Artificial Neural Networks (ICANN) proceedings. Published version copyrighted by Springer. This work was funded by the Horizon Europe Twinning project TERAIS, G.A. number 101079338 and in part by the national project APVV-21-0105.
Kovač, Luka, Farkaš, Igor
openaire +3 more sources

Formal Verification of Spatio-Temporal Rules Guided Safe Reinforcement Learning for CPS [PDF]

Jisuanji kexue yu tansuo
Deep reinforcement learning is currently a commonly used method in decision-making for cyber physical system (CPS). However, when facing an unknown environment and dealing with complex tasks, deep reinforcement learning based on black boxes cannot ...
YIN Chan, ZHU Yi, WANG Jinyong, CHEN Xiaoying, HAO Guosheng
doaj +1 more source

Is an Apple an Orange? A Large Language Model Benchmark for Candidate Term Extraction and Subclass Decisions Against Upper Ontologies in Engineering and Materials Science

Advanced Engineering Materials, EarlyView.
Building machine‐readable vocabularies for materials science is slow, expert‐driven work. This study benchmarks 13 large language models on two of its first steps: finding candidate terms in engineering articles and deciding where they belong in a class hierarchy.
Thomas Bjarsch +3 more
wiley +1 more source

Safe Reinforcement Learning via Curriculum Induction

CoRR, 2020
In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations during ...
Turchetta, Matteo +4 more
openaire +4 more sources

Conditional Sequence Modeling for Safe Reinforcement Learning

Mathematics
Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single policy capable ...
Wensong Bai +5 more
doaj +1 more source

Adaptive Foam 3D Printing of Ultralight and Multifunctional Materials

Advanced Engineering Materials, EarlyView.
Adaptive foam 3D printing, enabled by expandable microspheres, imparts cellular structures to thermoplastic and thermosetting polymers, manufactured through a variety of processes including fused filament fabrication, direct ink writing, digital light processing, and inkjet printing.
Nariman Rajabifar, Amir Ameli
wiley +1 more source

reinforcement learning
autonomous driving
deep reinforcement learning

safe exploration
safe learning
safe deep reinforcement learning

safety
constrained markov decision process
machine learning