AHMAD SULEMAN's Projects
Activity Recognition using Temporal Optical Flow Convolutional Features and Multi-Layer LSTM
Config files for my GitHub profile.
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Regularly Updated | Collection of the best Data Science and AI Material from the Web | Covering Everything from Books, Courses along with Material, Research Papers, and Interview Prep to Cheatsheet
Learned about search problems (A*, CSP, minimax), reinforcement learning, bayes nets, hidden markov models, and machine learning
Assistive Gym, a physics-based simulation framework for physical human-robot interaction and robotic assistance.
Automate approach to label images for object detection using TensorFlow
A open-source 2D bug robot simulator.
ChainerRL is a deep reinforcement learning library built on top of Chainer.
Official reinforcement learning environment for demand response and load shaping
source code
Best Practices, code samples, and documentation for Computer Vision.
Code that accompanies a blog posts on continuous online video classification with TensorFlow, Inception and a Raspberry Pi
Code for "Convolutional spiking neural networks (SNN) for spatio-temporal feature extraction" paper
List of papers, code and experiments using deep learning for time series forecasting
Repo for the Deep Reinforcement Learning Nanodegree program
Hands-on Deep Reinforcement Learning, published by Packt
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Code from the Deep Reinforcement Learning in Action book from Manning, Inc
Stochastic unit commitment model in python
Try out deep learning models online on Google Colab
TensorFlow documentation
We study the performance of various deep reinforcement learning algorithms for the problem of microgridโs energy management system. We propose a novel microgrid model that consists of a wind turbine generator, an energy storage system, a population of thermostatically controlled loads, a population of price-responsive loads, and a connection to the main grid. The proposed energy management system is designed to coordinate between the different sources of flexibility by defining the priority resources, the direct demand control signals and the electricity prices. Seven deep reinforcement learning algorithms are implemented and empirically compared in this paper. The numerical results show a significant difference between the different deep reinforcement learning algorithms in their ability to converge to optimal policies. By adding an experience replay and a second semi-deterministic training phase to the well-known Asynchronous advantage actor critic algorithm, we achieved considerably better performance and converged to superior policies in terms of energy efficiency and economic value.
Easy MDPs and grid worlds with accessible transition dynamics to do exact calculations
This is just to know how to use git hub
A robot powered training repository :robot:
OpenAI gym-based algorithm for the grid world problem
A toolkit for developing and comparing reinforcement learning algorithms.