Results (6)
Search Parameters:
Keyword: Q-Learning
Design Approach of an Electric Single-Seat Vehicle with ABS and TCS for Autonomous Driving Based on Q-Learning Algorithm
Compared to other types of autonomous vehicles, the single-seat is the simplest when designing, since its compact design makes it an option that can simplify different mechanical aspects and enhance those of greater importance such as the steering and the braking system. Likewise, the electronic and electrical design may be a great improvement on the…
Read More Q-Learning versus SVM Study for Green Context-Aware Multimodal ITS Stations
Intelligent Transportation Systems (ITS) applications can take big advantage of Context Awareness approaches. Parameters such as user mobility, passengers comfort reaction and pollution emission levels (CO2) can enrich such applications during the decision making phase. Moreover, the expanding in ITS services offers great opportunities for travelers to find the best route to reach their destinations…
Read More Modeling Control Agents in Social Media Networks Using Reinforcement Learning
Designing efficient control strategies for opinion dynamics is a challenging task. Understanding how individuals change their opinions in social networks is essential to countering malicious actors and fake news and mitigating their effect on the network. In many applications such as marketing design, product launches, etc., corporations often post curated news or feeds on social…
Read More A Self-Adaptive Routing Algorithm for Real-Time Video Transmission in VANETs
Given the strict Quality of Experience (QoE) and Quality of Service (QoS) criteria for video transmission, such as delivery ratio, transmission delay, and mean opinion Score (MOS), video streaming is one of the hardest challenges in Vehicular Ad-Hoc Networks (VANETs). Additionally, VANET attributes, including environmental impediments, fluctuating vehicle density, and highly dynamic topology, have an…
Read More A New Technique to Accelerate the Learning Process in Agents based on Reinforcement Learning
The use of decentralized reinforcement learning (RL) in the context of multi-agent systems (MAS) poses some difficult problems. The speed of the learning process for example. Indeed, if the convergence of these algorithms has been widely studied and mathematically proven, they suffer from being very slow. In this context, we propose to use RL in…
Read More Boltzmann-Based Distributed Control Method: An Evolutionary Approach using Neighboring Population Constraints
In control systems, several optimization problems have been overcome using Multi-Agent Sys- tems (MAS). Interactions of agents and the complexity of the system can be understood by using MAS. As a result, functional models are generated, which are closer to reality. Nevertheless, the use of models with permanent availability of information between agents is assumed…
Read More