Results 51 to 60 of about 13,931 (229)

Multi‐Agent Reinforcement Learning for Cyber Defence Transferability and Scalability

Applied AI Letters, Volume 7, Issue 1, February 2026.
A method for using mutli‐agent reinforcement learning that allows for zero shot transfer across network setups. Diagrams show the local observation construction, training and agent mapping process. The results for novel 15 and 30 node networks show effective transfer and improved scaling performance. ABSTRACT Reinforcement learning (RL) has shown to be
Andrew Thomas, Matthew Yates, Oliver Osborne   +2 more
wiley   +1 more source

Decision-Theoretical Navigation of Service Robots Using POMDPs with Human-Robot Co-Occurrence Prediction

International Journal of Advanced Robotic Systems, 2013
To improve the natural human-avoidance skills of service robots, a human motion predictive navigation method is proposed, namely PN-POMDP. A human-robot motion co-occurrence estimation algorithm is proposed which incorporates long-term and short-term ...
Kun Qian, Xudong Ma, Xianzhong Dai, Fang Fang, Bo Zhou   +4 more
doaj   +1 more source

UAV4PE: An Open-Source Framework to Plan UAV Autonomous Missions for Planetary Exploration

Drones, 2022
Autonomous Unmanned Aerial Vehicles (UAV) for planetary exploration missions require increased onboard mission-planning and decision-making capabilities to access full operational potential in remote environments (e.g., Antarctica, Mars or Titan ...
Julian Galvez-Serna, Fernando Vanegas, Shahzad Brar, Juan Sandino, David Flannery, Felipe Gonzalez   +5 more
doaj   +1 more source

Online Planning Algorithms for POMDPs

Journal of Artificial Intelligence Research, 2008
Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains. However, solving a POMDP is often intractable except for small problems due to their complexity. Here, we focus on online approaches that alleviate the computational complexity by computing good local ...
Ross, Stéphane, Pineau, Joelle, Paquet, Sébastien, Chaib-draa, Brahim   +3 more
openaire   +4 more sources

A Task and Motion Planning Framework for Partially Observable Household Manipulation Scenes

Advanced Intelligent Systems, Volume 7, Issue 12, December 2025.
This paper presents a novel TAMP framework tackling partial observability, cluttered scenes, and vague goals via symbolic reasoning and occlusion‐aware planning. It outperforms prior learning, policy, and LLM‐based methods in six real and simulated household tasks.
Yuhong Ma, Yeqing Yuan, Shaoquan Wu, Han Yuan   +3 more
wiley   +1 more source

Experimental results : Reinforcement Learning of POMDPs using Spectral Methods [PDF]

, 2017
We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods.
Anandkumar, Animashree, Azizzadenesheli, Kamyar, Lazaric, Alessandro   +2 more
core   +1 more source

Energy Efficient Execution of POMDP Policies [PDF]

IEEE Transactions on Cybernetics, 2015
Recent advances in planning techniques for partially observable Markov decision processes (POMDPs) have focused on online search techniques and offline point-based value iteration. While these techniques allow practitioners to obtain policies for fairly large problems, they assume that a nonnegligible amount of computation can be done between each ...
Grześ, Marek, Poupart, Pascal, Yang, Xiao, Hoey, Jesse   +3 more
openaire   +2 more sources

Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions

International Statistical Review, Volume 93, Issue 3, Page 385-424, December 2025.
Summary In recent years, reinforcement learning (RL) has acquired a prominent position in health‐related sequential decision‐making problems, gaining traction as a valuable tool for delivering adaptive interventions (AIs). However, in part due to a poor synergy between the methodological and the applied communities, its real‐life application is still ...
Nina Deliu, Joseph Jay Williams, Bibhas Chakraborty   +2 more
wiley   +1 more source

Sensor Synthesis for POMDPs with Reachability Objectives

, 2017
Partially observable Markov decision processes (POMDPs) are widely used in probabilistic planning problems in which an agent interacts with an environment using noisy and imprecise sensors.
Chatterjee, Krishnendu, Chmelik, Martin, Topcu, Ufuk   +2 more
core   +2 more sources

Monte Carlo Bayesian Reinforcement Learning [PDF]

, 2012
Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them.
Hsu, David, Lee, Wee Sun, Wang, Yi, Won, Kok Sung   +3 more
core   +1 more source