Results 21 to 30 of about 184,437 (258)
An ϵ-Greedy Multiarmed Bandit Approach to Markov Decision Processes
Stats, 2023 We present REGA, a new adaptive-sampling-based algorithm for the control of finite-horizon Markov decision processes (MDPs) with very large state spaces and small action spaces. We apply a variant of the ϵ-greedy multiarmed bandit algorithm to each stage
Isa Muqattash, Jiaqiao Hu
doaj +1 more source
Positivity-hardness results on Markov decision processes [PDF]
TheoretiCSThis paper investigates a series of optimization problems for one-counter Markov decision processes (MDPs) and integer-weighted MDPs with finite state space.
Jakob Piribauer, Christel Baier
doaj +1 more source
Feature Markov Decision Processes [PDF]
, 2008 General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes (MDPs). So far it is
Hutter, Marcus
core +4 more sources
UAV Formation Shape Control via Decentralized Markov Decision Processes
Algorithms, 2021 In this paper, we present a decentralized unmanned aerial vehicle (UAV) swarm formation control approach based on a decision theoretic approach. Specifically, we pose the UAV swarm motion control problem as a decentralized Markov decision process (Dec ...
Md Ali Azam +2 more
doaj +1 more source
Open Mathematics, 2023 This article presents an approximation of discrete Markov decision processes with small noise on Borel spaces with an infinite horizon and an expected total discounted cost by the corresponding deterministic Markov process.
Portillo-Ramírez Gustavo +3 more
doaj +1 more source
Percentile Queries in Multi-Dimensional Markov Decision Processes [PDF]
, 2015 Markov decision processes (MDPs) with multi-dimensional weights are useful to analyze systems with multiple objectives that may be conflicting and require the analysis of trade-offs.
C Baier +23 more
core +8 more sources
Accelerating Iterative Methods for Bounded Reachability Probabilities in Markov Decision Processes [PDF]
Computer and Knowledge Engineering, 2020 Probabilistic model checking is a formal method for verification of the quantitative and qualitative properties of computer systems with stochastic behaviors.
Mohammadsadegh Mohagheghi
doaj +1 more source
Learning Algorithms for Verification of Markov Decision Processes [PDF]
TheoretiCSWe present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive exploration of the ...
Tomáš Brázdil +8 more
doaj +1 more source
Multiple-Environment Markov Decision Processes [PDF]
, 2014 We introduce Multi-Environment Markov Decision Processes (MEMDPs) which are MDPs with a set of probabilistic transition functions. The goal in a MEMDP is to synthesize a single controller with guaranteed performances against all environments even though ...
Raskin, Jean-François, Sankur, Ocan
core +2 more sources
Foundations of probability-raising causality in Markov decision processes [PDF]
Logical Methods in Computer ScienceThis work introduces a novel cause-effect relation in Markov decision processes using the probability-raising principle. Initially, sets of states as causes and effects are considered, which is subsequently extended to regular path properties as effects ...
Christel Baier +2 more
doaj +1 more source