gayathrirangu Goto Github PK

abc.github.io

ashel-song

blinkingled-pin13-arduinomega

The Hello world of Arduino- Making the LED on pin13 blink! Best way to get started with Arduino programming.

bookticket

cpp-practice-codes

digitrecognition

This task of digit recognition is done using Hidden Markov Model using Speech signal as input. This model is written in C++ and is trained on custom-recorded digit dataset.

federated-learning-pytorch

Implementation of Communication-Efficient Learning of Deep Networks from Decentralized Data

federated-reinforcement-learning-annotated-papers

Notes and annotated papers related to Federated Reinforcement learning in robotics and RL in general.

gayathridevan_javascript

Addiing basic validations to a sign in form using JS

gayathrirangu-design-patterns

gayathrirangu.github.io

My personal website

gayathrirangu_cleancodeandserialisation

gayathrirangu_collection

gayathrirangu_designprinciples

A simple implementation of Calculator application using Spring framework to perform dependency injection (using XML configuration).

gayathrirangu_git

gayathrirangu_html-css

A basic Sign in form using HTML & CSS.

gayathrirangu_loggers

gayathrirangu_mavenoop

Implementing OOP concepts using Maven on Eclipse IDE.

genai-with-llms

grovelightsensorv1.1-arduinomega

Interface the Grove light intensity sensor v1.1 with Arduino Mega. The sensor is an Analog-to-Digital sensor. It takes in Analog values and outputs digital values (0-6455 approx.) in terms of Lux. The code is in C++ for Arduino.

marl-papers

Paper list of multi-agent reinforcement learning (MARL)

ml.ai-practice

This rep contains all my practice codes, material and notebooks, all the way from Python basics, libraries to ML algorithms to Ensemble Learning to to Neural Networks and Deep Learning concepts.

obstacle_avoidance_using_rl

A Webots robot is programmed to learn avoiding obstacles using model-free RL algorithms such as Q-Learning and State-Action-Reward-State-Action (SARSA).

portfolio.github.io

rainbow-dance

a demo dance repository

rainbowsong

reinforcement-learning-algo-implementations

These are some of my RL algorithm implementations as a part of my RL practice

ros1_noetic_codes

sample_codes_on_tartarus

Tartarus is a multi agent system. Its acts as a platform and facilitates creating, moving, cloning of the agents.

to-do-list