LLM-Driven Composite Neural Architecture Search for Multi-Source RL State Encoding

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Yu, Xie, Qian, Cao, Nairen, Jin, Li
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Systems and Control
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Geometry-Preserving Neural Architectures on Manifolds with Boundary
di: Elamvazhuthi, Karthik, et al.
Pubblicazione: (2026)

Enhancing Sample Efficiency in Multi-Agent RL with Uncertainty Quantification and Selective Exploration
di: Danino, Tom, et al.
Pubblicazione: (2025)

Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence
di: Wu, Yidan, et al.
Pubblicazione: (2025)

Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load Restoration
di: Abdeen, Zain ul, et al.
Pubblicazione: (2026)

STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order
di: Gu, Chengyang, et al.
Pubblicazione: (2026)

PowerFlowMultiNet: Multigraph Neural Networks for Unbalanced Three-Phase Distribution Systems
di: Ghamizi, Salah, et al.
Pubblicazione: (2024)

Naga: Vedic Encoding for Deep State Space Models
di: Schaller, Melanie, et al.
Pubblicazione: (2025)

Neural Operators for Multi-Task Control and Adaptation
di: Sewell, David, et al.
Pubblicazione: (2026)

Learning and Current Prediction of PMSM Drive via Differential Neural Networks
di: Mei, Wenjie, et al.
Pubblicazione: (2024)

Symptom-Driven Personalized Proton Pump Inhibitors Therapy Using Bayesian Neural Networks and Model Predictive Control
di: Li, Yutong, et al.
Pubblicazione: (2025)

Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
di: Li, Yaojun, et al.
Pubblicazione: (2026)

Large-scale Regional Traffic Signal Control Based on Single-Agent Reinforcement Learning
di: Li, Qiang, et al.
Pubblicazione: (2025)

SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning
di: Zolman, Nicholas, et al.
Pubblicazione: (2024)

Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem
di: Shao, Zhentong, et al.
Pubblicazione: (2025)

Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies
di: Cao, John, et al.
Pubblicazione: (2025)

ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
di: Xu, Yuezhu, et al.
Pubblicazione: (2024)

Physics-informed RL for Maximal Safety Probability Estimation
di: Hoshino, Hikaru, et al.
Pubblicazione: (2024)

Lyapunov Neural ODE State-Feedback Control Policies
di: Ip, Joshua Hang Sai, et al.
Pubblicazione: (2024)

FairMarket-RL: LLM-Guided Fairness Shaping for Multi-Agent Reinforcement Learning in Peer-to-Peer Markets
di: Jadhav, Shrenik, et al.
Pubblicazione: (2025)

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter
di: Xiong, Xi, et al.
Pubblicazione: (2019)

Data-Driven Adaptive PID Control Based on Physics-Informed Neural Networks
di: Ito, Junsei, et al.
Pubblicazione: (2025)

A Graph Neural Network with Auxiliary Task Learning for Missing PMU Data Reconstruction
di: Li, Bo, et al.
Pubblicazione: (2025)

Logarithmic Regret and Polynomial Scaling in Online Multi-step-ahead Prediction
di: Qian, Jiachen, et al.
Pubblicazione: (2025)

State Derivative Normalization for Continuous-Time Deep Neural Networks
di: Weigand, Jonas, et al.
Pubblicazione: (2024)

SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning
di: Xu, Jianye, et al.
Pubblicazione: (2024)

Multi-Target Radar Search and Track Using Sequence-Capable Deep Reinforcement Learning
di: Ewers, Jan-Hendrik, et al.
Pubblicazione: (2025)

Embedding Safety into RL: A New Take on Trust Region Methods
di: Milosevic, Nikola, et al.
Pubblicazione: (2024)

Hierarchical RL-MPC Control for Dynamic Wake Steering in Wind Farms
di: Nilsen, Marcus Binder, et al.
Pubblicazione: (2026)

A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning
di: Gokhale, Anand, et al.
Pubblicazione: (2026)

Physics-Informed Neural Networks for Accelerating Power System State Estimation
di: Falas, Solon, et al.
Pubblicazione: (2023)

Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees
di: Huang, Yanliang, et al.
Pubblicazione: (2026)

Efficient Sampling for Data-Driven Frequency Stability Constraint via Forward-Mode Automatic Differentiation
di: Xu, Wangkun, et al.
Pubblicazione: (2024)

Training Task Reasoning LLM Agents for Multi-turn Task Planning via Single-turn Reinforcement Learning
di: Hu, Hanjiang, et al.
Pubblicazione: (2025)

CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems
di: Patel, Sagar, et al.
Pubblicazione: (2023)

RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems
di: Siyadatzadeh, Roozbeh, et al.
Pubblicazione: (2025)

A semi-centralized multi-agent RL framework for efficient irrigation scheduling
di: Agyeman, Bernard T., et al.
Pubblicazione: (2024)

Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL
di: Anahtarci, Berkay, et al.
Pubblicazione: (2024)

Robust Power System State Estimation using Physics-Informed Neural Networks
di: Falas, Solon, et al.
Pubblicazione: (2025)

RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
di: Barbara, Nicholas H., et al.
Pubblicazione: (2023)

Composite Reward Design in PPO-Driven Adaptive Filtering
di: Bereketoglu, Abdullah Burkan
Pubblicazione: (2025)