Results 41 to 50 of about 45,379 (157)

Characterizing Markov Decision Processes [PDF]

, 2002
Problem characteristics often have a significant influence on the difficulty of solving optimization problems. In this paper, we propose attributes for characterizing Markov Decision Processes (MDPs), and discuss how they affect the performance of reinforcement learning algorithms that use function approximation.
Bohdana Ratitch, Doina Precup
openaire   +1 more source

Contextual Markov Decision Processes

CoRR, 2015
We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts. The new model, called Contextual Markov Decision Process (CMDP), can model a customer's behavior when interacting
Assaf Hallak, Dotan Di Castro, Shie Mannor   +2 more
openaire   +2 more sources

One-Counter Markov Decision Processes [PDF]

Proceedings of the Twenty-First Annual ACM-SIAM Symposium on Discrete Algorithms, 2010
Updated preliminary version, submitted to ...
T. Brazdil, V. Brozek, K. Etessami (Kousha), A. Kucera, D.K. Wojtczak (Dominik)   +4 more
openaire   +4 more sources

Creativity and Markov Decision Processes [PDF]

CoRR
Creativity is already regularly attributed to AI systems outside specialised computational creativity (CC) communities. However, the evaluation of creativity in AI at large typically lacks grounding in creativity theory, which can promote inappropriate attributions and limit the analysis of creative behaviour.
Guckelsberger Christian, Ady Nadia M., Lahikainen Joonas   +2 more
openaire   +4 more sources

Comparing Labelled Markov Decision Processes

CoRR, 2020
35 pages, 7 ...
Stefan Kiefer, Qiyi Tang 0001
openaire   +4 more sources

IoT Fog Computing Optimization Method Based on Improved Convolutional Neural Network

IEEE Access
The rapid development of communication technology has promoted the development of the Internet of Things technology. It has resulted in a scarcity of computing resources for the Internet of Things devices, and limited the further development of the ...
Bing Jing, Huimin Xue
doaj   +1 more source

Communicating via Markov Decision Processes

, 2021
ICML ...
Sokota, S, de Witt, CS, Igl, M, Zintgraf, L, Torr, P, Strohmeier, M, Kolter, JZ, Whiteson, S, Foerster, J   +8 more
openaire   +4 more sources

Data-Driven Volt/VAR Optimization for Modern Distribution Networks: A Review

IEEE Access
The Volt/Var optimization (VVO) enables advanced control strategy development for voltage regulation. With the recent advancement of data-driven approaches and communication infrastructure, realtime decision-making through VVO can effectively address ...
Sarah Allahmoradi, Shahabodin Afrasiabi, Xiaodong Liang, Junbo Zhao, Mohammad Shahidehpour   +4 more
doaj   +1 more source

Markov Decision Processing Networks

CoRR
We introduce Markov Decision Processing Networks (MDPNs) as a multiclass queueing network model where service is a controlled, finite-state Markov process. The model exhibits a decision-dependent service process where actions taken influence future service availability.
Sanidhay Bhambay, Thirupathaiah Vasantam, Neil Walton   +2 more
openaire   +2 more sources

Robust Synchronization in Markov Decision Processes [PDF]

, 2014
We consider synchronizing properties of Markov decision processes (MDP), viewed as generators of sequences of probability distributions over states. A probability distribution is p-synchronizing if the probability mass is at least p in some state, and a sequence of probability distributions is weakly p-synchronizing, or strongly p-synchronizing if ...
Doyen, Laurent, Shirmohammadi, Mahsa, Massart, Thierry   +2 more
openaire   +3 more sources