bhairavmehta95
on leave from my @mit EECS PhD, building B2B software. previously MS @mila-iqia. BS @umich, @nasa-jpl, @NVlabs.
@ :) New York, NY
Pinned Repositories
ant-env
Ant Gather and Ant Maze envs, separated from RLLab
asymmetric-actor-critic
Implementation of Asymmetric Actor Critic for Image-Based Robot Learning in Tensorflow.
carla-rl
Environments and Wrappers for CARLA, designed for ease of use with RL Tasks.
data-efficient-hrl
Implementation of Data Efficient Reinforcement Learning in Pytorch
slitherin-gym
Slither-in Inspired Snake Environment for OpenAI Gym (Part of Requests for Research 2.0)
depthfirstlearning.com
udem-fall19-public
Public accompanying repository for Universite de Montreal's IFT 6757: Autnonomous Vehicles, Fall 2019.
active-domainrand
Code repository for Active Domain Randomization (CoRL 2019, https://arxiv.org/abs/1904.04762)
domain-randomizer
A standalone library to randomize various OpenAI Gym Environments
sim-parameter-estimation
The code accompaniment for the CoRL 2020 paper: A User's Guide to Calibrating Robotics Simulators (https://arxiv.org/abs/2011.08985), from NVIDIA Research Seattle.
bhairavmehta95's Repositories
bhairavmehta95/slitherin-gym
Slither-in Inspired Snake Environment for OpenAI Gym (Part of Requests for Research 2.0)
bhairavmehta95/ant-env
Ant Gather and Ant Maze envs, separated from RLLab
bhairavmehta95/option-critic
Implementation of Option Critic with Deliberation Cost in Tensorflow
bhairavmehta95/ASD_VideoApp
An application to help all children (especially those with Autism Spectrum Disorder) interact with TV shows like Dora and Blue's Clues.
bhairavmehta95/3M_LED_Pi
Code to run on Raspberry Pi that works with 3M_LEDIndicator
bhairavmehta95/An-Information-Retrieval-Approach-to-Education-Systems
bhairavmehta95/ask-alexa-pykit
A minimalist SDK for developing skills for the Amazon Echo's ASK - Alexa Skills Kit using Amazon Web Services's Python Lambda Functions. Currently supported profiles are for Linux servers and AWS Lambda. Check the appropriate release branch. The cherrypy release branches have added components for request validation.
bhairavmehta95/cnn-surrogate
Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
bhairavmehta95/control
A repository for control benchmarking code
bhairavmehta95/duckietown-slimremote
Low-overhead low-latency high-frequency remote control library for the robot via ZMQ and OpenCV
bhairavmehta95/flashcard-helper-alexa-skill
Alexa Dorm Hack competition submission. 5th Place out of 45 submissions in Mind Sumo Challenge (https://www.mindsumo.com/contests/hack-the-dorm)
bhairavmehta95/flashcard-helper-eb
Elastic Beanstalk application that serves as a Quizlet account verification tool for the Alexa Skill Flashcard Helper.
bhairavmehta95/gap
Gazebo plugins for applying domain randomization
bhairavmehta95/gazebo_domain_randomization
Domain randomization for gazebo simulator
bhairavmehta95/hierarchical-ml
Library to Visualize and Train Hierarchical Data Sources
bhairavmehta95/JARVIS-on-Messenger
:speech_balloon: A community-driven python bot that aims to be as simple as possible to serve humans with their everyday tasks
bhairavmehta95/LED_Indicator
3M Led Indicator, By Ryan Pfalz & Bhairav Mehta
bhairavmehta95/mastering_ros
This repository contains exercise files of the book "Mastering ROS for Robotics Programming"
bhairavmehta95/MAT6115_Dynamical_Systems
Support material for MAT6115, Université de Montréal, Fall 2018
bhairavmehta95/MATLAB
MATLAB Code for Math 371 - Numerical Methods for Engineers and EECS 442 -Computer Vision
bhairavmehta95/mujoco
Python wrapper for MuJoCo physics simulation.
bhairavmehta95/neural-networks-and-deep-learning
My implementations alongside my notes. Using Tensorflow instead of Theano
bhairavmehta95/psketch
bhairavmehta95/rl_abstraction
Code for experimenting with state and action abstractions in reinforcement learning.
bhairavmehta95/ros-examples
Provides ROS examples for Snapdragon Flight Features, With Added Capabilities (Image Publisher)
bhairavmehta95/ros-gazebo-step
Exposes a ROS Service that allows for stepping of the Gazebo Simulator in terms of number of physics ODE iterations (which is useful for an RL setup).
bhairavmehta95/self-imitation-learning
ICML 2018 Self-Imitation Learning
bhairavmehta95/Smart-Whiteboard
bhairavmehta95/Stein-Variational-Gradient-Descent
code for the paper "Stein Variational Gradient Descent (SVGD): A General Purpose Bayesian Inference Algorithm"
bhairavmehta95/web-speech-api
A repository for demos illustrating features of the Web Speech API. See https://developer.mozilla.org/en-US/docs/Web/API/Web_Speech_API for more details.