ankur-deka Goto Github PK

followers: 37.0 following: 18.0 repos: 63.0 gists: 0.0

Name: Ankur Deka

Type: User

Company: Intel Labs

Bio: ML Robotics @ Tesla Optimus | AI Robotics Engineer @ Nimble Robotics | AI Research Engineer @ Intel Labs | MS in Robotics @ CMU RI | ECE & CS @ IIT Guwahati

Blog: https://ankur-deka.github.io/

This is the source code my homepage adopted from Jon Barron's public academic website. The following is his message:

You are welcome to clone his code for your own personal use, just please attribute the source to his original website or Jon Barron's repo. If you do clone this website, feel free to add an attribution link to your own downstream website in index.html if you want.

Ankur Deka's Projects

6dof-graspnet

Implementation of 6-DoF GraspNet with tensorflow and python. This repo has been tested with python 2.7 and tensorflow 1.12.

a-star

Simple Visual A-Star

actor-residual-critic

ARC - Actor Residual Critic for Adversarial Imitation Learning

agents

TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.

ankur-deka.github.io

Website to describe my projects

auto-encoder

Encoder Decoder architecture for MNIST Compression

carvana-challenge

My repository for the Carvana Image Masking Challenge

cmu-ri-presentation-template

Unofficial PowerPoint presentation template for CMU Robotics Institute

coding

Coding in CPP and Python

convert-data

Convert Data into usable format

create_dataset

Generic Module for Creating Image Dataset

data-structures-and-algorithms

Implementation of popular DS and Algo

deep-reinforcement-learning-algorithms-with-pytorch

PyTorch implementations of deep reinforcement learning algorithms and environments

emergent-multiagent-strategies

Emergence of complex strategies through multiagent competition

f-irl

Inverse Reinforcement Learning via State Marginal Matching - CoRL 2020

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-cloth

Code for fabric smoothing https://sites.google.com/view/fabric-smoothing. No further updates are expected.

gym-cooking

gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of CogSci 2020 conference award in computational modelling.