Constrained reinforcement learning

Results 61 to 70 of about 6,930,474 (290)

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

Chance-Constrained Control With Lexicographic Deep Reinforcement Learning [PDF]

IEEE Control Systems Letters, 2020
This paper proposes a lexicographic Deep Reinforcement Learning (DeepRL)-based approach to chance-constrained Markov Decision Processes, in which the controller seeks to ensure that the probability of satisfying the constraint is above a given threshold.
Giuseppi A., Pietrabissa A.
openaire +5 more sources

Machine Learning‐Supported Analysis for Predicting and Visualizing Nonlinear Relationships Between Material Properties in Electroplated Chromium Layers

Advanced Engineering Materials, EarlyView.
This study applies machine learning regression to predict chromium layer thickness in decorative trivalent chromium electroplating, using 441 experiments from laboratory‐scale (1L) and pilot‐scale (14L) setups. Tree‐based models, particularly CatBoost, outperformed linear regression by capturing nonlinear parameter interactions (R2$R^2$ up to 0.77 ...
Christoph Baumer +4 more
wiley +1 more source

Safe Robot Navigation Using Constrained Hierarchical Reinforcement Learning

, 2023
737742Safe navigation is one of the steps necessary for achieving autonomous control of robots. Among different algorithms that focus on robot navigation, Reinforcement Learning (and more specifically Deep Reinforcement Learning) has shown impressive ...
Ning, Xiangyu +4 more
core +1 more source

Bidirectional reinforcement learning neural network for constrained molecular design

Scientific Reports
We present BiRLNN, a bidirectional molecular design framework that combines recurrent neural networks with reinforcement learning to optimize drug-like properties of generated compounds.
Junan Lin +5 more
doaj +1 more source

Adaptive Client Selection in Resource Constrained Federated Learning Systems: A Deep Reinforcement Learning Approach

IEEE Access, 2021
With data increasingly collected by end devices and the number of devices is growing rapidly in which data source mainly located outside the cloud today.
Hangjia Zhang +4 more
doaj +1 more source

New AI‐Assisted Approach for Expanding the Solution Space: Application to Lattice Structure Design

Advanced Engineering Materials, EarlyView.
This work introduces an innovative framework for designing structured materials by ex panding the design space through reparameterization of qualitative variables into continuous structural descriptors. Combined with machine‐learning‐based prediction and multi‐objective optimization, the approach enables the discovery of novel lattice architectures ...
G. H. Gahimbare +5 more
wiley +1 more source

Policy Gradients for Probabilistic Constrained Reinforcement Learning

2023 57th Annual Conference on Information Sciences and Systems (CISS), 2023
This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the system in a safe set with high probability.
Weiqin Chen 0003 +2 more
openaire +2 more sources

DigiChrom: A Domain Ontology for Semantic Representation of Trivalent Chromium Platings and Its Large Language Model‐Based Alignment With Multiple Mid‐Level Ontologies

Advanced Engineering Materials, EarlyView.
Digitalizing electroplating requires both domain knowledge and interoperability. This work introduces PlatOn, a domain ontology for trivalent chromium plating and coating characterization, and a hybrid pipeline that aligns it to a mid‐level reference ontology by combining eight similarity metrics with language model reasoning. Expert‐validated mappings
Janik Harter +10 more
wiley +1 more source

Constrained Intrinsic Motivation for Reinforcement Learning

CoRR
Accepted by IJCAI ...
Xiang Zheng +3 more
openaire +3 more sources

reinforcement learning
deep reinforcement learning
safe reinforcement learning

medicine