ngoodger Goto Github PK

ai_lab

alpine-vim

"dockerized" Vim

arduino-soft-core

binary-adder-rnn-notebook

Binary adder Recurrent Neural Network (RNN) Implemented in Tensorflow in a Jupyter notebook. RNN is also wrapped with a simple calculator so it is possible to manually test inputs.

ckanext-privatedatasets

CKAN extension that allows a user to create private datasets only visible to certain users. The extension provides also an API to specify which users can access private datasets

clevr_robot_env

CLEVR-Robot: a reinforcement learning environment combining vision, language and control.

cptk2barracuda

Tensorflow saved model to unity barracuda .nn file. (*.cptkから*.nnに変換）

dynamic_topology

Exploring dynamic topology

finetune_gptneo_gptj6b

Repo for fine-tuning GPTJ and other GPT models

garden

getoldtweets-python

A project written in Python to get old tweets, it bypass some limitations of Twitter Official API.

legnav_firmware

Firmware for lego robot to test navigation algorithms. Written in NXC programming language.

model_predictive_control_test

Experiment in Model Predictive Control using Deep Learning

nle-language-wrapper

Nethack Learning Environment Wrapper for Language Interface

pong-from-pixels

Training a Neural Network to play Pong from pixels

predict-rnn-position-from-timing-advance

puzzle_world_rl

Experiment in solving a simple puzzle

pytari2600

python based atari 2600 emulator

python_find_and_replace

Find and replace in files or filenames using Python dictionary to define mapping

python_max_autolint

Code autoformatting and linting using Python Black and Flake8. Aims for maximum automation.

pytorch_search_testing

Just testing the ability of an RNN to learn a deterministic policy of hard attention. Intention was to test the feasibility of Reinforcement Learning for hard attention.

pytorch_simple_linear_regression

rl-course-easy21

robot_grasp

tensorforce

TensorForce: A TensorFlow library for applied reinforcement learning

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

v157

Proceedings of ACML 2021

vimrc

My Personal .vimrc configuration.

zuki

Reinforcement Learning Library