Latest Articles for Policy

This article examines the methods for creating safe autonomous vehicles.

Exploring the regulatory landscape of generative AI and its implications.

New tree structures improve decision-making visibility in AI systems.

Research on how harmful agents can corrupt good agents in decentralized RL.

A method for finding strategies in MDPs without prior knowledge.

A simplified model for effective navigation using natural language instructions.

Young people's views on the smoke-free generation policy are essential for its success.

This article discusses methods for verifying neural networks in reach-avoid tasks.

MOMBO enhances decision-making in offline reinforcement learning with improved uncertainty estimation.

SeMOPO improves learning from low-quality data by separating useful information from noise.

This framework enhances learning efficiency in complex tasks through hierarchical structures.

New framework blends rewards and constraints in reinforcement learning.

Exploring the gap in Internet access across Brazilian cities and its impact.

This article discusses strategies for effective collateral management in layer-two blockchain systems.

CMDPs merge reward maximization with safety in AI applications.

A new algorithm combines offline RL and preference feedback for improved decision-making.

An innovative approach to efficient feedback collection in reinforcement learning for safety.

This article examines Natural Policy Gradient for efficient decision-making in large state spaces.

A new method improves decision-making under uncertainty using robust Markov Decision Processes.

Exploring the connection between reinforcement learning and ethical decision-making in machines.

RPO improves decision-making speed and safety in reinforcement learning through reflective learning.

Examining how machine learning transforms employment opportunities in Canada.

Combining Hamilton-Jacobi reachability with reinforcement learning enhances safety in control systems.

A new method proposes a better way for robots to learn tasks efficiently.

A new method enhances robot exploration and goal achievement through temporal distance.

A new policy aims to reduce smoking rates among young adults.

Sharing experiences to improve future robotic development.

This study focuses on offline reinforcement learning and algorithm development to improve decision-making.

Researchers propose a new method for robot locomotion focusing on foot placement.

Examining how outdoor ads influence diets and health in Xela.

This article discusses the development of winning policies across families of MDPs.

Exploring strategies for effective communication in product adoption.

A look into the challenges and collaborative efforts surrounding rare diseases in India.

A new method enhances RL agents' adaptability to changing environments.

Introducing PromptAdapt for improved adaptability in robots with minimal training.

A new framework improves agent-based modeling by integrating diverse expert insights.

Re-thinking MDPs through geometry for efficient decision-making.

aBCF enables better evaluation of interventions across individuals and groups.

Caution-Aware Transfer enhances safety and performance in reinforcement learning applications.

A novel approach to generate policies that cater to different preferences.