Results 71 to 80 of about 13,256,052 (164)

Robust Markov Decision Processes [PDF]

Markov decision processes (MDPs) are powerful tools for decision making in uncertain dynamic environments. However, the solutions of MDPs are of limited practical use due to their sensitivity to distributional model parameters, which are typically ...
Berç Rustem, Wolfram Wiesemann, Daniel Kuhn   +2 more
core  

Constraints Driven Safe Reinforcement Learning for Autonomous Driving Decision-Making

IEEE Access
Although reinforcement learning (RL) methodologies exhibit potential in addressing decision-making and planning problems in autonomous driving, ensuring the safety of the vehicle under all circumstances remains a formidable challenge in practical ...
Fei Gao, Xiaodong Wang, Yuze Fan, Zhenhai Gao, Rui Zhao   +4 more
doaj   +1 more source

CMDP based adaptive power management in server clusters

, 2013
Many high-end computing systems use a large number of power-hungry commercial components to improve performance. Thus power reduction and energy conservation are important in these systems for the purpose of reducing operating costs.
Cai, Yu, Zheng, Xinying
core   +1 more source

Risk-aware Path Planning Using Hirerachical Constrained Markov Decision Processes

, 2014
— Next generation industrial plants will feature mo-bile robots (e.g., autonomous forklifts) moving side by side with humans. In these scenarios, robots must not only maximize efficiency, but must also mitigate risks.
Stefano Carpin, Seyedshams Feyzabadi
core   +1 more source

Safe deep reinforcement learning method for guaranteed compliance with physical constraints in autonomous energy systems of critical infrastructure (a case study of healthcare facilities)

Авіаційно-космічна техніка та технологія
The study examines the complex processes of intelligent management of energy resilience in modern healthcare facilities during critical situations, large-scale failures, and prolonged outages of the external centralized power supply.
Maksym Kushnarov
doaj   +1 more source

Deep Reinforcement Learning-Enhanced Multi-Objective Cold-Chain Vehicle Routing with Dynamic Order Insertion and Carbon Emission Constraints

Journal of Applied Science and Engineering
Cold-chain logistics is critical for preserving perishable goods but faces challenges of high operational costs, carbon emissions, and dynamic order uncertainties.
Qinqin Zhang
doaj   +1 more source

Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes [PDF]

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.
Romberg, Justin, Zeng, Sihan, Doan, Thinh T.   +2 more
core  

Symbolic Magnifying Lens Abstraction in Markov Decision Processes [PDF]

, 2008
In this paper, we combine abstraction-refinement and symbolic techniques to fight the state-space explosion problem when model checking Markov decision processes (MDPs).
Luca de Alfaro, Parker, D., David Parker, de Alfaro, L., Pritam Roy, Norman, G., Roy, P., Gethin Norman   +7 more
core   +1 more source

Online learning in stochastic and adversarial constrained Markov decision processes [PDF]

LAUREA MAGISTRALEI moderni processi decisionali richiedono sempre più spesso la capacità di adattarsi a contesti incerti e dinamici, le cui condizioni non sono note in anticipo e possono evolvere in modo imprevedibile nel tempo.
CHIEFARI, ELEONORA FIDELIA
core  

On principle of optimality for safety-constrained Markov Decision Process and p-Safe Reinforcement Learning [PDF]

We study optimality for the safety-constrained Markov decision process which is the underlying framework for safe reinforcement learning. Specifically, we consider an undiscounted safety-constrained Markov decision process subject to random stopping ...
Misra, Rahul; id_orcid, Wisniewski, Rafal   +1 more
core   +1 more source