Latest Articles for Markov Decision Processes

This article discusses a new perspective on Markov Decision Processes for multi-agent systems.

Improving efficiency of probability estimates in uncertain systems through advanced methods.

This article discusses a distributed method for traffic management using connected vehicles.

Improving safety and efficiency in self-driving cars through better communication.

A new approach to enhance learning in infinite-horizon average-reward MDPs.

Examining how creativity can be assessed in artificial intelligence systems.

A data-driven method for optimizing drone deliveries in real-time.

An overview of policy gradient methods in reinforcement learning.

A method for finding strategies in MDPs without prior knowledge.

Exploring how inexact policy iteration aids decision-making in uncertain environments.

Exploring federated control in reinforcement learning for agents to work together securely.

Discover how lazy abstraction and BRTDP improve MDP analysis efficiency.

A new framework for improved decision-making in dynamic situations.

A new method enhances agent learning in reinforcement learning environments.

A new method enhances decision-making in uncertain environments using Monte-Carlo Tree Search.

Exploring a new method for safe data collection in policy evaluation.

This article discusses improving electron injection efficiency at BESSY II through machine learning techniques.

New frameworks enhance decision-making learning from expert behavior.

ICU-Sepsis aids researchers in testing AI algorithms for better sepsis management.

A look into policy iteration methods for effective decision-making and their verification.

This article discusses using certificates and witnesses in verifying multi-objective queries in MDPs.

Introducing an efficient algorithm for reinforcement learning with deterministic dynamics.

Exploring new methods for effective reinforcement learning in continuous settings.

Study enhances lane-changing strategies for self-driving cars in mixed traffic.

A new approach to quantify uncertainty in systems using MDPs.

A method to derive cost functions by analyzing expert actions in complex environments.

This method improves agent training using less expert data through exploration and path signatures.

Learn how MMDPs improve decision-making in uncertain environments.

A look into MDPs and their role in decision-making under uncertainty.

Explore how Markov Decision Processes aid in managing uncertain outcomes with risk considerations.

Using symmetry to enhance learning efficiency in aircraft control algorithms.

This article discusses methods to keep agents' decision-making processes private.

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

New methods improve decision-making in various fields through reinforcement learning.

A new approach improves decision-making in AI through causal relationships.

Learn how Markov Decision Processes improve decision-making in uncertain scenarios.

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

Improving seed order fulfillment processes to enhance agricultural efficiency.

Exploring new methods for better decision-making under uncertainty in AI systems.

This article discusses the complexities of choosing sensors and actuators in systems.