jperl

famous-meteor

Example with famo.us, meteor, and iron-router

karma-cucumber

Please use s9tpepper/karma-cucumberjs instead

mbta-sign

🚆Power an RGB sign + Rasberry Pi with ETAs for the mbta

meteor-chrome-extension

A simple chrome extension example that is built to work with the meteor parties example

paper

🎴Facebook paper in javascript. Run the example w/ device emulation on

rl-homework

🤖 RL homework for Berkeley CS294-112 (Fall 18) and Sutton book

stock2vec

📈 Stock embeddings based on PE context

xor

⊕ OpenAI Warmup: LSTM to solve XOR

qawolf

🐺 Create browser tests 10x faster

jperl/angular-jquery-mobile

A todo example with angular, jquery mobile, and tested with karma & travis. Explanation video here http://youtu.be/hNAHogdcus0

jperl/xor

⊕ OpenAI Warmup: LSTM to solve XOR

jperl/rl-homework

🤖 RL homework for Berkeley CS294-112 (Fall 18) and Sutton book

jperl/meteor-linkedin

LinkedIn accounts OAuth flow

jperl/atari-reset

Code for the blog post "Learning Montezuma’s Revenge from a Single Demonstration"

jperl/autologin

A project to attempt to automatically login to a website given a single seed

jperl/planet

Deep Planning Network: Control from pixels by latent planning with learned dynamics

jperl/rrweb-snapshot

rrweb's snapshot and rebuild module

jperl/classifier-builder

jperl/Curiosity_Driven_Goal_Exploration

Code to reproduce the results of "Curiosity Driven Exploration of Learned Disentangled Goal Spaces"

jperl/Deep-Learning-Papers-Reading-Roadmap

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

jperl/deep-pensieve

A Residual Multi-Stage Maximum Mean Discrepancy Variational Resize-Convolution Auto-Encoder with Group Normalization

jperl/DeepMimic

Motion imitation with deep reinforcement learning.

jperl/docker-squid4

Squid 4 docker container

jperl/dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

jperl/E-DRL

Exploration Strategies for Deep Reinforcement Learning

jperl/homework

Assignments for CS294-112.

jperl/MINERVA

Meandering In Networks of Entities to Reach Verisimilar Answers

jperl/ncp

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors

jperl/Pedestrian-Detector

Pedestrian detection using the TensorFlow Object Detection API. Includes multi GPU parallel processing inference.

jperl/puppetcam

Export puppeteer tab as webm video

jperl/pytorch-retinanet

Pytorch implementation of RetinaNet object detection.

jperl/random-network-distillation

jperl/reaction-next-starterkit

Reaction Commerce's headless ecommerce storefront - Next.js, GraphQL, React

jperl/reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

jperl/rlkit

Collection of reinforcement learning algorithms

jperl/rrweb-player

jperl/Variational_Discriminator_Bottleneck

Implementation (with some experimentation) of the paper titled "VARIATIONAL DISCRIMINATOR BOTTLENECK: IMPROVING IMITATION LEARNING, INVERSE RL, AND GANS BY CONSTRAINING INFORMATION FLOW" (arxiv -> https://arxiv.org/pdf/1810.00821.pdf)

jperl/warcreate

Chrome extension to "Create WARC files from any webpage"

jperl/WorldModelsExperiments

World Models Experiments