vjg28

Varshil Gandhi's repositories

Linear-Inverse-RL-algorithms

Implementation of Linear Inverse Reinforcement Learning Algorithm (IRL) on Mountain Car Environment.

Language:Jupyter NotebookMIT29 1 1

BERT_on_NarrativeQA

This repository is an application of BERT Language Model on NarrativeQA dataset.

Language:Python2 20

NLP_RL

NLP_RL (Just a test trial)

Language:Python2 1 1

Device-for-ship-detection

This low cost device is designed to be kept on small fishing boats having no safety systems for avoiding collisions with big ships.- Refer to the document attached for detailed documentation

Language:C++MIT1 10

Fake-News-Detection

A fake-news detector model based on BERT trained and evaluated on Liar-Plus dataset.

Language:PythonMIT1 3 1

Huffman-Coding-ARM

Huffman Encoding application in ARM (College Project)

Language:Assembly1 10

robotic-palm

A live camera based framework that controls the motion of the robotic palm in accordance to the human palm.

Language:PythonApache-2.01 10

ARLE

An Automated Library Bot to help keep the Lakshminath Bezbaroa Library, IIT Guwahati arranged.

Language:Makefile010

Lunar-Lander-RL

This code base is an attempt to design an agent using Monte-Carlo Policy Gradient algorithm without / with baseline function.

Language:Python010

Reinforcement-Learning-Algorithms

This repository contains codes and explanation to underlying algoritms of reinforcement learning tested on various games of OpenAI gym. (Documentation under progress)

Language:Jupyter NotebookMIT010