Pinned Loading

1. Multiagent Reinforcement Learning project to handle collaborate and compete scenarios for Tennis Unity environment. MADDPG algorithm is used to solve the environment.

   Jupyter Notebook 1

2. Continuous Control using DDPG Algorithm

   Jupyter Notebook

3. Deep Q Network project which navigates a environment to collect bananas. This project is dones as part of Udacity's Deep Reinforcement Nanodegree

   Python

4. This is my Computer Vision capstone project in the Udacity AI Nanodegree program! This project demonstrates using computer vision techniques and deep learning to build and end-to-end facial keypoin…

   HTML

5. Recurrent Neural Networks: Time series prediction and Text generation

   HTML

6. Convolutional Neural Networks (CNN) project: Project builds a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, algorithm wi…

   HTML