reinforcement learning

Physical embodiment enables information processing beyond explicit sensing in active matter

Living microorganisms have evolved dedicated sensory machinery to detect environmental perturbations, processing these signals through biochemical networks to guide behavior. Replicating such capabilities in synthetic active matter remains a fundamental challenge. Here, we demonstrate that synthetic active particles ca...

Autonomous alignment of a Mach-Zehnder interferometer via deep reinforcement learning: a foundation for resilient space-based and ground-based optical control

This paper presents a Deep Reinforcement Learning (DRL) framework for the autonomous alignment of a Mach-Zehnder Interferometer (MZI). Utilizing a Proximal Policy Optimization (PPO) algorithm and a Convolutional Neural Network (CNN) policy, the agent manages two-degree-of-freedom mirror adjustments to achieve a null-fr...

HAMRL: a hierarchical attention-based multi-agent reinforcement learning approach for IoT-based service composition

Highly Configurable Evolutionary Multi‐Objective Optimisation and Application in UAV Path Planning

ABSTRACT Multi‐objective optimisation is crucial in engineering and real‐world decision‐making. Although traditional decomposition‐based approaches such as MOEA/D yield reasonable results, they depend heavily on expert knowledge. Existing MetaBBO approaches partially alleviate this reliance, however, they offer limited...

Attractor count in collective reinforcement-learning dynamics depends on interaction structure, not on population size

Code, saved results and paper for the interaction-structure result in collective reinforcement-learning dynamics.

Replication Data for: GA-MARL: Graph Attention Multi-Agent Reinforcement Learning for Information-Synergistic Airspace Hazardous Zone Detection and Inversion

GA-MARL: Graph Attention Multi-Agent Reinforcement Learning for Information-Synergistic Airspace Hazardous Zone Detection and Inversion

Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning

Topology optimization of electromagnetic devices is computationally formidable owing to the combinatorial on/off material distribution on unstructured finite element meshes and repeated Maxwell equation solves. This paper develops GPRL-TO, a data-driven framework addressing both difficulties through three synergistic c...

Designing organic photoredox catalysts as a fragment-based puzzle solved by reinforcement learning

Reinforcement learning (RL) is a promising strategy for identifying optimal solutions in vast search spaces. We have developed a framework in which the design of organic photoredox catalysts (OPCs) is deliberately formulated as a fragment-based puzzle that is well suited to RL. In this framework, an RL agent sequential...

Prior preferences interfere with the associative learning of food values

Addressing unhealthy behaviors requires learning and implementing healthier options. Ecologically, we rarely undergo associative learning in naive environments; our prior preferences confound the learning process. This is perhaps especially true for food, for which we have strong, diverse preferences that may undermine...

Reward-Quality Divergence (RQD): Code, Saved Runs and Analysis Scripts (Anonymous Review Artifact)

Anonymous review artifact for the paper Reward-Quality Divergence: Telling Judge Gaming from Judge Error in Visual RL. Please do not try to identify the authors. RQD measures the gap between a judge's reward and an anchor-based quality score during reinforcement learning, subtracts the gap that exists before training (...

Code and data for a controlled study of batch reinforcement learning for stepwise composition of strip-packing heuristic components

Python code and data for stepwise composition of classic best-fit-family components with tree-based Fitted Q Iteration: the configurable constructive engine, FQI/Double-DQN training pipelines, pre-registered control arms, all experiment runners, benchmark instances, per-run raw results (CSV), and the trained per-fold m...

Fisher Information Geometry, Reinforcement Learning, and Two-Layer Stochastic Approximation: From Prefill–Decode Dynamics to Multiscale Coupled Systems