akshaykulkarni3467 Goto Github PK

anime-project

Creating an anime portfolio using sheryjs library

astar-algo-visualization

Creating a visualization for A* algorithm with heuristic function of manhattan distance using pygame.

automated-snakeandapple

Training an agent to play snake and apple using stable baselines3 on a custom environment created by openai-gym

basicgateswithnn

Training a self developed neural network to predict output of basic gates like AND, OR, XOR

bella-project

An animated website using gsap and barba.js

bipelwalker-ddpg

Training Bipedal Walker of openai gym on DDPG algorithm. This algorithm is used to find deterministic policies over a continuous action space.

blackjackrl

Playing Blackjack using Monte Carlo learning with the epsilon greedy strategy.

blog-page-with-react-and-gsap

Developing a web page for init

cellular-automata

Generating cellular automata in python using pygame library

curiousitydrivena3c

Training an agent to explore a hallway using A3C algorithm and Intrinsic Curiousity Module RL.

deepq-networks

Implementing deep q-networks for the cart pole problem in reinforcement learning.

dex-tracker

An app which shows your crypto market trades and tracks anamolies in transactions of any address provided

dungeon_blockchain

A decentralized social media platform which is built on a blockchain for transfer of funds and rewards between influencers and small creators.

food-guesser

Developing a cnn model using mini dataset of Food101 which seperates the food into pizza, steak and sushi

frankaemikarobot

Training a virtual franka emika robot with SAC algorithm and Hindsight Experience Replay buffer.

gan-using-tensorflow

Developing a generative adversarial network to generate 28x28 pixel images of clothes

generative-audio-vae

Generating audio samples using variational autoencoder.

humanoid-automation

Using SAC algorithm to train the humanoid in mujoco environment.

imagecompression-svd

Compressing an image with singular value decomposition using numpy

imitationlearning-automatedcar

Using imitation learning (DAgger algorithm) to solve the CarRacing environment in openai-gym.

machine-learning

Learning various ml models

machine-translation

Implementing transformer architecture from scratch and training it to perform English to Italian translation.

ml_xgboostalgo

multiarmedbandit

Here, we solve the multi-armed bandit problem using a classical epsilon-greedy agent with reward-average sampling as the estimate to action-value Q.

naf_dqn

DQN for contineous action spaces by using normalized advantage function (NAF). This project intends to solve the lunarLander environment of openai-gym.

naivebayesclassifier

Creating a naive bayes classifier with numpy to create a confusion matrix of any categorical data

nlp-specialization

Coursework and Assignments for natural language processing specialization by deeplearning.ai

pca-on-mnist

Applying PCA to reduce features of the mnist dataset from 785 to 100 using concepts of eigenvalues,eigenvectors and SVD

pickndropgame

Implementing the Q learning algorithm by PicknDrop game. Here a carrier has to pickup a client and drop him off to the specified location.

pixel-grid

Pixel grid places any design on a surface of an image while keeping the objects on the surface in place. You can resize, reshape and rotate the design as per your need.