tjujianyu Goto Github PK

actormimic

Train an RL agent to play multiple Atari games at once

afedrl

that is the code corresponding to papper "Automatic Feature Engineering by Deep Reinforcement Learning" in AAAI'19

afem

That is the code corresponding to paper "Towards Automatic Complex Feature Engineering" in WISE

autoencoders_cf

billiard_dataset

cafem

Source code for "Cross-data Automatic Feature Engineering via Meta-learning and Reinforcement Learning"

datasciencecourse

This holds iPython notebooks and lecture slides for the Intro to Data Science Master's course I teach at NYU.

deep_reinforcement_learning_course

Notebooks from our series of blogpost about Deep Reinforcement Learning

ds_1001_git_start

explorekit

featencode

featuretools

automated feature engineering

gradient_starvation

Gradient Starvation: A Learning Proclivity in Neural Networks

hindsight-experience-replay

Hindsight Experience Replay - Bit flipping experiment in Tensorflow

keras-gan

Keras implementations of Generative Adversarial Networks.

llama.cpp

Port of Facebook's LLaMA model in C/C++

maml

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

maml_rl

Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

memorymosaics

Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.

nfs

nyu_hpc

ssh connection, jupyter connection, sublime text, slurm, etc.

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

representation_based_rs

rfc

rl-adventure

Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL

rrl

Rich Representation Learning

ssi_dataset

A dataset for slient speech interface

ssi_dl

silent speech interface by deep learning

ssiwave

tencentads_18

DNN solution for Tencent advertisement challenge http://algo.qq.com/home/information/info.html