Essays about: "Experience Replay"

Showing result 1 - 5 of 14 essays containing the words Experience Replay.

  1. 1. Utilizing energy-saving techniques to reduce energy and memory consumption when training machine learning models : Sustainable Machine Learning

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

    Author : Khalid El Yaacoub; [2024]
    Keywords : Sustainable AI; Machine learning; Quantization-Aware Training; Model Distillation; Quantized Distillation; Siamese Neural Networks; Continual Learning; Experience Replay; Data Efficient AI; Energy Consumption; Energy-Savings; Sustainable ML; Computation resources; Hållbar maskin inlärning; Hållbar AI; Maskininlärning; Quantization-Aware Training; Model Distillation; Quantized Distillation; siamesiska neurala nätverk; Continual Learning; Experience Replay; Dataeffektiv AI; Energiförbrukning; Energibesparingar; Beräkningsresurser;

    Abstract : Emerging machine learning (ML) techniques are showing great potential in prediction performance. However, research and development is often conducted in an environment with extensive computational resources and blinded by prediction performance. READ MORE

  3. 2. "We're here, and we don't know why" : An analysis of the postmodernist rejection of a universal meaning to life in Ken Grimwood’s novel Replay

    University essay from Jönköping University/Högskolan för lärande och kommunikation

    Author : Samuel Berglund; [2023]
    Keywords : ;

    Abstract : The question of the meaning of life is at the centre of this study without being directly addressed. The study does not analyse the meaning of life but rather how the main characters of the novel Replay (Jeff and Pamela) approach the question. READ MORE

  4. 3. Stabilizing Side Effects of Experience Replay With Different Network Sizes for Deep Q-Network

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

    Author : Simon Granström; [2023]
    Keywords : ;

    Abstract : This report investigates the effects of two different types of batch selection used for traininga Deep Reinforcement Learning agent in games. More specifically, the impact of thedifferent methods were tested for different sizes of Deep Neural Networks while using theDeep Q-Network (DQN) algorithm. READ MORE

  5. 4. Deep Reinforcement Learning for Dynamic Grasping

    University essay from Uppsala universitet/Avdelningen för systemteknik

    Author : Andreas Ström; [2022]
    Keywords : Deep Reinforcement Learning; Dynamic Grasping; DDPG; HER; Robotics;

    Abstract : Dynamic grasping is the action of, using only contact force, manipulating the position of a moving object in space. Doing so with a robot is a quite complex task in itself, but is one with wide-ranging applications. READ MORE

  6. 5. Deep reinforcement learning for real-time power grid topology optimization

    University essay from Lunds universitet/Matematisk statistik

    Author : Jacob Rothschild; [2021]
    Keywords : Deep reinforcement learning; Dueling Deep Q-Network; electricity transmission network; real-time topology optimization; sustainable energy; Mathematics and Statistics;

    Abstract : In our pursuit of carbon neutrality, drastic changes to generation and consumption of electricity will cause new and complex demands on the power grid and its operators. A cheap, promising, and under-exploited mitigation is real-time power grid topology optimization (RTTO). READ MORE