AleksandarHaber/Deep-Q-Learning-Network-from-Scratch-in-Python-TensorFlow-and-OpenAI-Gym AleksandarHaber/Deep-Q-Learning-Network-from-Scratch-in-Python-TensorFlow-and-OpenAI-Gym

  • Stars
    star
    6
  • Rank 2,539,965 (Top 51 %)
  • Language
    Python
  • Created almost 2 years ago
  • Updated almost 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
AleksandarHaber/Deep-Q-Learning-Network-from-Scratch-in-Python-TensorFlow-and-OpenAI-Gym
github

AleksandarHaber

Reviews

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

Repository Details

These code files implement the deep Q learning network algorithm from scratch by using Python, TensorFlow, and OpenAI Gym. The codes are tested in the OpenAI Gym Cart Pole (v1) environment.

More Repositories

1

Subspace-Identification-State-Space-System-Identification-of-Dynamical-Systems-and-Time-Series-

Python
27
star
2

Machine-Learning-of-Dynamical-Systems-using-Recurrent-Neural-Networks

This project deals with learning to reproduce the input-output behavior of state-space models using recurrent neural networks and the Keras machine learning toolbox.
Python
21
star
3

Machine-Learning-and-System-Identification-for-Adaptive-Optics

This project deals with system identification and machine learning of large-scale deformable mirrors used in adaptive optics. I have submitted two papers that deal with this important problem. The approaches can be generalized two other problems of estimating large-scale system with the dynamics described by partial differential equations.
MATLAB
11
star
4

Save-and-Load-Eigen-Cpp-Matrices-Arrays-to-and-from-CSV-files

The functions provided in this C++ source files are used to save and load Eigen C++ matrices/arrays to and from CSV values.
C++
10
star
5

Model-Reference-Adaptive-Control---MIT-Rule

MATLAB
10
star
6

Simulation-of-State-Space-Models-of-Dynamical-Systems-in-Cpp--Eigen-Matrix-Library-Tutorial

C++
8
star
7

Introduction-to-Eigen-Cpp-Matrix-Computation-Library

This C++ code explains how to use the Eigen C++ library to perform matrix computations. A video lecture and a post accompanying this code is provides.
C++
7
star
8

Machine-learning-of-ARX-models-of-Dynamical-Systems-using-Keras-and-MLP

Python
6
star
9

Graphics-User-Interface-in-Cpp-and-Plotting-Using-Qt-QCustomPlot-and-Eigen-Matrix-Library

This project demonstrates how to develop graphic user interfaces in C++ using the Qt development environment. Also, we demonstrate how to couple Eigen matrix library with QCustomPlot Qt library to generate graphs and plots in C++
C++
6
star
10

Sparse-Approximate-Inverse-of-a-Sparse-Matrix--MATLAB-Implementation

This is a MATLAB function that computes an approximate (sparse) inverse of a sparse matrix.
MATLAB
5
star
11

PID-control-implementation-Arduino-Ball-and-Beam-System

This is a C/C++ Arduino file that implements a PID controll algorithm for a ball and beam system.
C++
4
star
12

Introduction-to-Time-Series-Analysis-and-Estimation-in-Python

These are the codes that support the lectures on time-series analysis and estimation in Python.
Python
4
star
13

matlab_arduino_interface

This is a MATLAB-Arduino interface for controlling mechatronics devices directly from MATLAB. It uses a serial port communication
C++
3
star
14

Sensor-Selection-for-Nonlinear-Networks

In this repository, we post MATLAB algorithms for selecting nodes of networks with nonlinear dynamics.
MATLAB
3
star
15

Modeling-of-Mirror-Temperature-Dynamics-and-Model-Order-Reduction

MATLAB
3
star
16

Simple-Latex-Template

This is a simple latex template. This template accompanies the YouTube video I made.
TeX
3
star
17

Low-Cost-Brain-Computer-Interface-by-Using-OpenBCI-Cython-Board-MATLAB-and-Arduino

This repository contains MATLAB and Arduino C codes for establishing a low-cost brain computer interface. The brain computer interface is based on the Cython OpenBCI board, MATLAB, Arduino, and a stepper motor.
C++
3
star
18

Monte-Carlo-Method-for-Estimating-State-Value-Function-in-Python-

This code implements the (first visit) Monte Carlo method for estimating the state value function in Python.
Python
3
star
19

Execute-Python-Code-From-MATLAB

These code files explain how to execute Python code directly from MATLAB
MATLAB
2
star
20

Machine-Learning-and-Identification-of-Temperture-Dynamics

2
star
21

Disciplined-Kalman-Filter-Implementation-in-Python

This code implements the Kalman filter in Python by using an object oriented approach.
Python
2
star
22

Kalman-Filter-Implementation-in-Cpp-Using-Eigen-Library

C++
2
star
23

Demonstration-of-Meshgrid-and-3D-Plotting-in-Python

Python
2
star
24

Iterative-Policy-Evaluation-Algorithm-and-OpenAI-Gym

This code implements the iterative policy evaluation algorithm in Python. We use the Frozen Lake environment from OpenAI Gym library to illustrate the performance of the iterative policy evaluation algorithm.
Python
2
star
25

Introduction-to-Scikit-learn-Classification-and-Visualization

Python
2
star
26

Linear-Quadratic-Regulator-With-Nonzero-Set-Points-in-MATLAB

MATLAB
2
star
27

Plot-Phase-Portraits-and-State-Space-Trajectories-of-Dynamical-Systems-in-MATLAB

In this tutorial, we explain how to generate phase portraits and state-space trajectories of dynamical systems in MATLAB.
MATLAB
2
star
28

Disciplined-Python-Implementation-of-the-Recursive-Least-Squares-Method

This is a disciplined Python implementation of the Recursive Least Squares Method
Python
2
star
29

C-code-Arduino-for-the-Weightlifter-Project

This is an Arduino (C code) for controlling the experimental setup "Arduino Weightlifter". Here is the YouTube video of the project: https://www.youtube.com/watch?v=Fj_0KRzNGfA This code is written by Francesco Pecora (undegraduate student) and Aleksandar Haber (professor) CUNY College of Staten Island April 2018
C++
2
star
30

Q-Learning-Algorithm-in-Python-with-Cart-Pole-OpenAI-Gym--Gymnasium-Environment

In this repository, we post the implementation of the Q-Learning (Reinforcement) learning algorithm in Python. The codes are tested in the Cart Pole OpenAI Gym (Gymnasium) environment.
Python
2
star
31

Control-Node-Selection-and-Control-Action-Design-for-Nonlinear-Networks-and-Systems

These are the codes for optimally selecting control nodes and computing control actions for networks with nonlinear dynamics and systems.
MATLAB
2
star
32

Demonstration-of-Cart-Pole-OpenAI-Gym-Reinforcement-Learning-Environment-in-Python-

This code file demonstrates how to use the Cart Pole OpenAI Gym (Gymnasium) environment in Python.
Python
2
star
33

Brief-Intro-to-Multiclass-Classification-in-Scikit-learn-and-Python

Python
1
star
34

Implementation-of-Voting-Classifier-in-Scikit-learn-and-Python---Ensemble-Machine-Learning

Python
1
star
35

Demonstration-of-Inheritance-in-Cpp

C++
1
star
36

Extended-Kalman-Implementation-in-Python

Python
1
star
37

transient-structural-thermal-optical-performance-STOP-analysis-of-reflective-optics

This code repository contains COMSOL Multiphysics and MATLAB files used to perform transient (time-dependent) Structural Thermal Optical Performance (STOP) analysis of reflective optics. We perform the transient STOP analysis of a Newtonian telescope.
1
star
38

Bagging-Classifier-in-Python

In this repository, we posted the codes that demonstrate how to implement the Bagging classifier in the Scikit-learn library and Python.
Python
1
star
39

Three-must-know-approaches-for-computing-the-Fibonacci-sequence-in-Cpp

C++
1
star
40

Solve-Nolinear-Equations-in-Python-by-Using-fsolve

Python
1
star
41

Policy-Iteration-Algorithm-in-Python-with-Tests-on-Frozen-Lake-OpenAI-Gym-Environment

Reinforcement Learning Tutorial. Implementation of the Policy Iteration Algorithm in Python Tested on the Frozen Lake OpenAI Gym environment.
Python
1
star
42

Multi-Armed-Bandit-Problem-and-Epsilon-Greedy-Action-Value-Method-in-Python

This GitHub repository contains Python implementation of the epsilon-greedy action value method for solving multi-armed bandit problem.
Python
1
star
43

ROS_modeling_using_xacro_and_urdf

These repository contains xacro/urdf and launch files necessary to model a robot.
1
star
44

Machine-learning-of-transient-structural-thermal-optical-peformance-STOP-models

This code repository contains Python codes that are used for estimating structural thermal optical performance (STOP) models of optical systems
1
star
45

Simulation-of-Differential-Equations-in-Python-with-Time-Varying-Inputs-and-Parameters

Python
1
star
46

aleksandarhaber.github.io

This is my webpage/blog.
HTML
1
star
47

System-Identification-of-Structural-Thermal-Optical-Performance-STOP-models

This code repository contains system identification codes for estimating structural-thermal-optical-performance (STOP) models of reflective optics. Also, this repository contains COMSOL LiveLink for MATLAB codes that are used to generate system identification and validation data.
1
star
48

Demonstration-of-Vector-Containers-in-Cpp-Standard-Template-Library-STL-

This file demonstrates how to use and perform basic operations on vector containers in C++ Standard Template Library (STL). The tutorial webpage accompanying this code file is given here:
C++
1
star
49

Introduction-to-Recurrent-Neural-Networks-in-Keras-and-TensorFlow

Python
1
star
50

Phase-portraits-of-dynamical-systems-and-state-space-models-in-Python

In this Python dynamical system tutorial, we explain how to construct phase portraits of dynamical systems and state-space models. The posted code will construct a phase portrait and a state-space trajectory of a dynamical system. The webpage tutorial accompanying these codes is given here: https://aleksandarhaber.com/phase-portraits-of-state-space
Python
1
star
51

SARSA-Temporal-Difference-Learning-in-Python

These code files implement the on-policy SARSA (State-Action-Reward-State-Action) reinforcement learning algorithm in Python.
Python
1
star
52

Introduction-to-OpenAI-Gym-Python-Library-and-Frozen-Lake-Reinforcement-Learning-Environment

This code demonstrates how to use OpenAI Gym Python Library and Frozen Lake Environment. This code accompanies the tutorial webpage given here:
Python
1
star
53

Greedy-in-the-Limit-with-Infinite-Exploration-GLIE-Monte-Carlo-Reinforcement-Learning-in-Python

The Python codes given here, explain how to implement the Greedy in the Limit with Infinite Exploration (GLIE) Monte Carlo Control Method in Python. We use the OpenAI Gym (Gymnasium) to test the Python codes. More precisely we use the Frozen Lake Environment to test the GLIE Monte Carlo Control method.
Python
1
star