Deep Reinforcement Learning projects

May 21, 2020

These 3 projects are implementations made for the udacity’s nanodegree program, all passed through a reviewer. They contain a small report, gathering my comprehension fo the algorithm as well as details on my implementation and my parameters.

  • First project: P1 Navigation.
    Implementation of a DQN algorithm with uniformly sampled as well as prioritized Replay Buffer, with learning performance comparison.
  • Second project: P2 Continuous Control.
    Implementation of a DDPG algorithm with uniformly sampled Replay Buffer and UONoise modeling exploration. Soft update was also used between target and local networks.
  • Third project: P3 Collaborative Navigation.
    Implementation of a DQN algorithm with uniformly sampled as well as prioritized Replay Buffer, with learning performance comparison.
Deep Learning Python Computer Vision Reinforcement Learning ipynb Deep Reinforcement Learning
Avatar
Thomas Di Martino
PhD Student in AI & Remote Sensing

My research interests include deep learning technologies, automatic feature extraction and computer vision, all of them applied to Remote Sensing problematics, more precisely to Synthetic Aperture Radar (SAR) acquisitions.

Related