reinforcement learning

A KG-DRL framework for post course competition certificate integration and path generation in civil aviation vocational colleges

Abstract The “Post-Course-Competition-Certificate” (PCCC) integration model has emerged as a cornerstone of vocational education reform in China, yet its implementation in civil aviation vocational colleges is hindered by the absence of quantifiable fusion criteria, reliance on subjective evaluation practices, and the...

Blockchain-assisted IoT-based smart electric vehicle network for secure data sharing and authentication

Experiments conducted in a controlled simulation environment show that BFGRL can effectively improve security, trust management, scalability, and operational efficienssssscy in blockchain-assisted smart EV networks.

Introduction to Additive Manufacturing, Artificial Intelligence, and Machine Learning

Additive Manufacturing (AM), also known as 3D printing, has revolutionised traditional production methods by enabling layer-by-layer fabrication of complex geometries with reduced waste and enhanced customisation. This chapter provides a brief introduction to AM key processes such as Vat Photopolymerisation, Material E...

Safeguarded Reinforcement Learning for Dynamic Environments

Purely machine learning‐based control strategies often suffer from the lack of safety guarantees. In this manuscript, we introduce a locally applied fallback controller to safeguard Deep Reinforcement Learning in dynamic environments. The fallback controller takes over whenever a safety criterion would otherwise be v...

Physics-guided deep reinforcement learning framework for reliability-based design optimization of complex mechanical systems

Reliability-based design optimization (RBDO) is essential for the safe and economical operation of complex mechanical systems, whose time-dependent performance must continuously satisfy safety requirements under multi-source stochasticity and multiple progressive damage. However, conventional RBDO methods face an inher...

The Play Loop

This chapter introduces play loops as a constructional framework for engaging learners and building instruction from interaction rather than control. A play loop is a mutually sustained, reciprocally reinforcing chain in which each participant’s action both signals the next response and reinforces the previous one. Rat...

Reinforcement Learning-based Constant Flux Control of Membrane Filtration Process

Submerged membrane bioreactor (SMBR) systems offer high treatment efficiency and compact operation, but nonlinear dynamics and time-varying membrane fouling make constant-flux regulation challenging. This study develops and evaluates three reinforcement-learning controllers—a deep Q-network (DQN), deep deterministic po...

Error-driven representation learning in the mesolimbic system

In reinforcement learning, an agent learns to map representations of the environment state to predictions of future reward. Most prior work in neuroscience has assumed a fixed representation and studied how reward prediction errors (thought to be conveyed by phasic dopamine signals) are used to update the mapping from...

Extending Goal-Oriented Specification for Reinforcement Learning to High Dimensions

Reviewer #3 (Public review): Error-driven representation learning in the mesolimbic system

In reinforcement learning, an agent learns to map representations of the environment state to predictions of future reward. Most prior work in neuroscience has assumed a fixed representation and studied how reward prediction errors (thought to be conveyed by phasic dopamine signals) are used to update the mapping from...

Reviewer #2 (Public review): Error-driven representation learning in the mesolimbic system

In reinforcement learning, an agent learns to map representations of the environment state to predictions of future reward. Most prior work in neuroscience has assumed a fixed representation and studied how reward prediction errors (thought to be conveyed by phasic dopamine signals) are used to update the mapping from...

eLife Assessment: Error-driven representation learning in the mesolimbic system

In reinforcement learning, an agent learns to map representations of the environment state to predictions of future reward. Most prior work in neuroscience has assumed a fixed representation and studied how reward prediction errors (thought to be conveyed by phasic dopamine signals) are used to update the mapping from...