reinforcement learning

Dynamic Adaptive Optimizer and Reinforcement Learning Integration

This paper presents a novel dynamic adaptive optimization framework combining reinforcement learning with a dynamically adjusting optimization strategy. The core focus is on optimizing complex, non-structured problems, leveraging reinforcement learning to learn an optimized objective function and dynamically adjust the...

Title: Universal Constraint Induction (UCI) for Dynamical Systems

Universal Constraint Induction (UCI) presents a novel framework for automatically generating and verifying constraints for complex dynamical systems, facilitating the creation of entirely new and unpredictable system behavior. This work introduces a constraint-discovery algorithm leveraging Generative Adversarial Netwo...

Supplementary Data for: Bridging formal topologies and graph-embedded deep reinforcement learning for maintenance scheduling in high-energy irradiation facilities

This dataset contains the supplementary material supporting the manuscript "Bridging formal topologies and graph-embedded deep reinforcement learning for maintenance scheduling in high-energy irradiation facilities". It includes the Master Sequence of Operations (SOP) generated by the GCN-TD3 optimizer to achieve the 7...

Dynamic Programming with State Abstraction for Reinforcement Learning

Reinforcement learning (RL) relies heavily on dynamic programming (DP) to find optimal policies. However, the curse of dimensionality significantly limits its applicability in environments with large or continuous state spaces. Traditional DP methods become computationally intractable, often requiring exponential time...

Dynamic Graph Partitioning for Distributed Deep Learning

Distributed deep learning has emerged as a crucial paradigm for training increasingly complex models, often necessitating the partitioning of computational graphs across multiple devices. However, traditional graph partitioning techniques rely on static heuristics, failing to adapt to the dynamic and evolving workload...

Title: Universal Constraint Induction (UCI) for Dynamical Systems

Universal Constraint Induction (UCI) presents a novel framework for automatically generating and verifying constraints for complex dynamical systems, facilitating the creation of entirely new and unpredictable system behavior. This work introduces a constraint-discovery algorithm leveraging Generative Adversarial Netwo...

Dynamic Programming with State Abstraction for Reinforcement Learning

Reinforcement learning (RL) relies heavily on dynamic programming (DP) to find optimal policies. However, the curse of dimensionality significantly limits its applicability in environments with large or continuous state spaces. Traditional DP methods become computationally intractable, often requiring exponential time...

Dynamic Topology Dependency Learning (TDTL)

This paper introduces Dynamic Topology Dependency Learning (TDTL), a novel approach to neural architecture search (NAS) that leverages the inherent dependencies within network topology to achieve more efficient architecture optimization. The core idea is to train a "topology controller" using reinforcement learning (RL...

Design of an Iterative AI-Driven Optimization of High-Ductility Concrete with Recycled Glass Fiber and Industrial Slag for Seismic Resilience Sets

SRTS: Semantic Representations for Trajectory Stitching in Offline Reinforcement Learning

Neuro-Topology Adaptive Dynamics

This paper introduces Neuro-Topology Adaptive Dynamics (NTAD), a novel approach to neural network design that leverages reinforcement learning to dynamically optimize the topology of a neural network. The core claim is that by adapting the network's connectivity structure in real-time, using algorithms like Proximal Po...

Title: Universal Chaos Theory with Adaptive Parameter Tuning

This paper explores a novel approach to understanding and manipulating universal chaos within complex systems, moving beyond static parameter settings. We propose a method based on Bayesian inference and reinforcement learning to dynamically optimize parameters of a chaotic system, fostering stable, high-dimensional st...