Cybernetic1/reinforcement-learning-experiments

Stars
7
Rank 2,294,772 (Top 46 %)
Language
Python
Created over 4 years ago
Updated 10 months ago

Cybernetic1/reinforcement-learning-experiments

Cybernetic1

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Reinforcement learning experiments with Tic Tac Toe, especially with "logical representations"

conceptual-keyboard-v1_bad

Conceptual Keyboard

AGI-16

"An AGI architecture in vector space" Paper to be submitted to AGI-16

2022

my Latex works 2022

2023

YKY's Latex works 2023

neural-network-in-C

Neural network code in C/C++

genifer5

Genifer - general inference engine, version 5

DecodingLaw

Deep learning for legal domain

intro-2-strong-AI

book: "Introduction to strong AI"

genifer5C

Genifer 5 prototype written in C

latex-2018

My latex documents in 2018, including the new Genifer white paper.

GIRL

Genetic inductive learning of logic rules

latex

My main latex dir, including misc files and oft-used symbols

paranoia

My autobiography in Latex

bookcam

Book Camera program suite

Cybernetic1.github.io

Coco -- collaborative platform based on virtual shares

genifer-scala-old

Genifer 3.0 (general inference engine), in Scala

COCO

COCO collaborative platform (world-wide version)

genifer4

Genifer 4 theoretical notes

COCO-China

Coco 合作平台 (China version)

2021

Latex stuff in 2021

AGI-21

AGI 2021 Conference paper: "AGI via combining logic with deep learning"

symmetric-NN

Symmetric neural network based on the form f(x,y) = g(h(x) + h(y), from the PointNet and DeepSet papers

2020

YKY's Latex writings 2020