cipollone Goto Github PK

artrecyclegan

Implementation of CycleGAN with Tensorflow 2.x

atarieyes

RL & Feature extraction on the Atari Games.

cipollone.github.io

cipollone2.github.io

escape-room1

An environment with Non-Markovian transitions: get the key and leave the room

gym-sapientino-case

A specific instance of the gym-sapientino environments

interact-webgl

keras-rl

Deep Reinforcement Learning for Keras.

maxout-nn

Easily write and train Maxout networks

merge-log

Merge experiments log files from different runs

mergetb

Export TensorBoard scalars to CSV file columns

minimoore

Moore machines and transducers (work in progress)

ml-notes-logistic

On section of the notes I've written while studying "Machine Learning: A Probabilistic Perspective, Kevin P. Murphy"

multinav

Multiple Navigation environments

multinav2

multittrust.github.io

Multittrust workshop website.

pycparser

:snake: Complete C99 parser in pure Python

python-template

A template for starting Python 3 projects

quadfields

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

recurrl2

RL with recurrent networks, v2

rl-experiments

A protocol for specifying reinforcement learning experiments

rlss-practice1

robotics-tools

ros-stage-rl

spmatch

C++ implementation of PatchMatch Stereo for images

stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

stage-controls

An interface for stage simulator

trace-dfa

Finds the minimum DFA (automaton) from a set of sequences in input

training-paths

Tiny library to create directories to save logs and models for learning.