Deep reinforcement learning aided packet-routing for aeronautical ad-hoc networks formed by passenger planes

D Liu, J Cui, J Zhang, C Yang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… In this paper, we invoke deep reinforcement learning for routing in AANETs aiming at …
To boost the learning efficiency and the online adaptability of the proposed DQN-routing, …

A reinforcement learning approach to a single leg airline revenue management problem with multiple fare classes and overbooking

A Gosavii, N Bandla, TK Das - IIE transactions, 2002 - Taylor & Francis
… If the passengers whose itinerary originates from Detroit form the highest class, those flying …
of passengers in the plane. See also Fig. I, which shows how the class of the passenger can …

A bounded actor–critic reinforcement learning algorithm applied to airline revenue management

RJ Lawhead, A Gosavi - Engineering Applications of Artificial Intelligence, 2019 - Elsevier
… 4 passengers per day was used; the plane was assumed to have a total capacity of 100
seats. The Poisson process for each fare class will hence be an independent process, whose …

[PDF][PDF] Aircraft Traffic Control with Reinforcement Learning

A Rasheed, A Alam, J Melloni, R Domingo - 2022 - asharalam11.github.io
… the SARSA reinforcement learning algorithm to manipulate the trajectories of the planes to
… Initially, it was used for military aircraft, but with the advent of passenger and cargo planes, …

A Novel Deep Reinforcement Learning Approach for Real-Time Gate Assignment

H Li, X Wu, M Ribeiro, BF Santos, P Zheng - Available at SSRN 4808146 - papers.ssrn.com
… However, unlike domestic passengers, international travelers must go through customs and
… two types of planes, airports must use a specific bridge to segregate the passenger flow line, …

A reinforcement learning algorithm based on policy iteration for average reward: Empirical results with yield management and convergence analysis

A Gosavi - Machine Learning, 2004 - Springer
… the lowest fare class of passengers in the plane. See also figure 2, which explains this idea.
A circle in figure 2 represents the origin and the symbol inside it indicates the class of the …

Research on arrival aircraft sequencing based on reinforcement learning

Y Wang, X Li - Sixth International Conference on Computer …, 2023 - spiedigitallibrary.org
… Due to the rapid development of China's aviation industry, the need for both passenger … ,
and gave the calculation results of 20 planes. Milan introduces the concept of priority queues to …

Hyperheuristic approach based on reinforcement learning for air traffic complexity mitigation

P Juntama, D Delahaye, S Chaimatanan… - Journal of Aerospace …, 2022 - arc.aiaa.org
… [39 – 42], most of the existing online learning hyperheuristics are reinforcement learning (RL)
mechanisms that use reward and punishment schemes [43] in the hyperheuristic …

[HTML][HTML] General real-time three-dimensional multi-aircraft conflict resolution method using multi-agent reinforcement learning

Y Chen, Y Xu, L Yang, M Hu - Transportation Research Part C: Emerging …, 2023 - Elsevier
Reinforcement learning (RL) techniques have been studied … general multi-agent reinforcement
learning approach for real-… 2D planes instead of the more complex 3D planes. These 2D …

Soft actor-critic deep reinforcement learning for fault tolerant flight control

K Dally, EJ Van Kampen - AIAA Scitech 2022 Forum, 2022 - arc.aiaa.org
… An offlinetrained cascaded Soft Actor-Critic Deep Reinforcement Learning controller is …
This section introduces the learning framework used in this research, actor-critic RL and the …