Essays about: "policy gradient"

Showing result 21 - 25 of 44 essays containing the words policy gradient.

1. 21. Generation and Detection of Adversarial Attacks for Reinforcement Learning Policies

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Axel Drotz; Markus Hector; [2021]
   Keywords : Deep Reinforcement Learning; Adversarial Attacks; Adversarial Attack Detection; Fast Gradient Sign Method; Deep Deterministic Policy Gradient; Deep Q-Learning; Likelihood Ratio Test; CUSUM;

   Abstract : In this project we investigate the susceptibility ofreinforcement rearning (RL) algorithms to adversarial attacks.Adversarial attacks have been proven to be very effective atreducing performance of deep learning classifiers, and recently,have also been shown to reduce performance of RL agents. READ MORE

3. 22. Bayesian Reinforcement Learning Methods for Network Intrusion Prevention

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Antonio Frederico Nesti Lopes; [2021]
   Keywords : Network Security; Reinforcement Learning; Bayesian Q-Learning; Bayesian Policy Gradient; Bayesian Actor-Critic; Markov Security Games; Nätverkssäkerhet; förstärkningslärande; Bayesian Q-Learning; Bayesian Policy Gradient; Bayesian Actor-Critic; Markov Security Games;

   Abstract : A growing problem in network security stems from the fact that both attack methods and target systems constantly evolve. This problem makes it difficult for human operators to keep up and manage the security problem. READ MORE

4. 23. A Comparison Between Deep Q-learning and Deep Deterministic Policy Gradient for an Autonomous Drone in a Simulated Environment

   University essay from Mälardalens högskola/Akademin för innovation, design och teknik

   Author : Dennis Tagesson; [2021]
   Keywords : ;

   Abstract : This thesis investigates how the performance between Deep Q-Network (DQN) with a continuous and discrete state- and action space, respectively, and Deep Deterministic Policy Gradient (DDPG) with a continuous state- and action space compare when trained in an environment with a continuous state- and action space. The environment was a simulation where the task for the algorithms was to control a drone from the start position to the location of the goal. READ MORE

5. 24. A Graph Attention plus Reinforcement Learning Method for Antenna Tilt Optimization

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Tengfei Ma; [2021]
   Keywords : Graph Attention; Reinforcement Learning; Antenna Tilt Optimization; 5G; Attention Mechanism; Graph; DQN; Back- Propagation; Gradient Descent;

   Abstract : Remote Electrical Tilt optimization is an effective method to obtain the optimal Key Performance Indicators (KPIs) by remotely controlling the base station antenna’s vertical tilt. To improve the KPIs aims to improve antennas’ cooperation effect since KPIs measure the quality of cooperation between the antenna to be optimized and its neighbor antennas. READ MORE

6. 25. Intelligent control of shared electric vehicle charging robots

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Mohd Aiman Khan; [2021]
   Keywords : ;

   Abstract : Electric Vehicles (EVs) sales have grown at an exponential rate all over the world. However, the industry still faces many challenges like high cost of electric vehicles, range anxiety and lack of access to efficient charging infrastructure. READ MORE