Name: Erfan Miahi
Type: User
Company: University of Alberta
Bio: Currently engrossed in the field of RL < Mainly interested in discovering the proper mathematical definition of Intelligence < ML Researcher
Twitter: erfan_mhi
Location: Canada, Edmonton
Blog: https://www.linkedin.com/in/erfan-miahi-8637a1130/
Erfan Miahi's Projects
This is log of my 100 days of ML code challenge.
My 2-page CV
Implementation of a Quantum inspired genetic algorithm proposed by A quantum-inspired genetic algorithm for k-means clustering paper.
A library of reinforcement learning components and agents
Adaptive Model-based Transfer Evolutionary Algorithm implementation in python
Solutions of Applied Data Science with python assignments will be here.
This repository contains solved assignments of Applied Plotting, Charting & Data Representation in Python course
:zap: Delightful Node.js packages and resources
A categorized list of representation learning papers that are focused on solving reinforcement learning problems
This is the code-base that I personally use as the starting point for any reinforcement learning codebase with the purpose of fast experimentation and analysis.
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Implementation of Cooperative Coevolution Transfer Optimization Algorithm
Solutions for Stanford CS224n: Natural Language Processing with Deep Learning
Stanford University cs224n Assignments solutions
My Latex Resume
The Leek group guide to data sharing
Deep learning summer school assignments
Solutions of assignments of Deep Reinforcement Learning course presented by the University of California, Berkeley (CS285) in Pytorch framework
Solutions of the assignments of Deep Reinforcement Learning (CS285) course presented by the UC Berkeley
Trying different Neural network models to see how they work on digit recognizer challenge by Kaggle.
My CV
This project is a chat application written with javafx
Flood it game implemented in VHDL
Implementation of Genetic Algorithm for feature selection of neural networks proposed by Genetic algorithm-based heuristic for feature selection in credit risk assessment paper.
A toolkit for developing and comparing reinforcement learning algorithms.
A set of environments which can be used to show how Reinforcement Learning algorithms address the exploration-exploitation dilemma.
This is the implementation of the 2-state MDP that is used in the mellowmax paper to show that softmax is not a non-expansion.