KaleabTessera/Policy-Gradient

Stars
1
Language
Python
Created about 5 years ago
Updated almost 2 years ago

KaleabTessera/Policy-Gradient

KaleabTessera

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Implementation of the following Policy Gradient Algorithms -Reinforce and Actor Critic.

DQN-Atari

Deep Q-Learning (DQN) implementation for Atari pong.

Research-Paper-Reading-Template

A markdown template for taking notes to summarize research papers.

PRM-Path-Planning

Implementation of Probabilistic Roadmap Path Planning Algorithm.

Multi-Armed-Bandit

Implementation of greedy, E-greedy and Upper Confidence Bound (UCB) algorithm on the Multi-Armed-Bandit problem.

ICOOmen_ML_Model

IcoOmen, a machine learning model which will predict the value of an ICO token after 6 months. This uses historic data that has been aggregated from various public websites and APIs (Application programming interfaces), as well as data that has been manually collected and calculated.

Jupyter Notebook

KnapSackProblem

Knapsack Problem implemented in Python. This includes a Linear Greedy and Quadratic Knapsack Implementation.

Jupyter Notebook

ROS-TurtleBot-Obstacle_Detection

An simple implementation of obstacle detection, using Rospy Turtlebot's depth camera and OpenCV.

NeuralNetwork_From_Scratch

An implementation of a Fully-connected Neural Network build from Scratch - only using Numpy.

TravellingSalesman

A 2-opt algorithm implementation of the Travelling Salesman Problem

Jupyter Notebook

SimulatedAnnealing

Implementation of the Simulated Annealing Algorithm in solving the (Symmetric) Travelling Salesman Problem.

Gridworld-Markov-Decision-Process

Implementing a gridworld from scratch and configuring it as a Markov decision process.

Jupyter Notebook

DroneFlight-Ros

Ardrone flight using PID.

PythonForMachineLearning

A collection of information on Python, specifically related to machine learning.

Jupyter Notebook

personal-site-v2

My personal website.

rospy-turtlebot-move-and-rotate

Basic Rospy code to get a turtlebot to move forward and rotate.

Obstacle-Tower-RL

K-nearest-neighbour-in-C

KNN in C, comparing performance of serial and parallel implementations (implemented in OpenMp).

Turtlebot-Kuri-Navigation

A Turtlebot and Kuri were both given a challenge of navigating an obstacle course.

Image-Convolution-Using-CUDA-C

Image Convolution Using CUDA C

SARSA_Cliffwalking

Implementation of SARSA for cliffwalking environment.

Jupyter Notebook

Monte-Carlo-and-Temporal-Difference

Monte Carlo and Temporal Difference implementation from Chapter 5 and Chapter 6 of Reinforcement Learning: An Introduction Book by Andrew Barto and Richard S. Sutton.

IcoOmenAPI

API layer behind IcoOmen.