Aaron Hosford's repositories
stable-baselines
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
SHRDLUBlocks
A simple environment for evaluating and testing natural language understanding systems
pyramids_categories
Pyramids Categories: Pre-compiled category files for the Pyramids Parser
LabyBot
Clone and solver of the Laby game
DefinitionOfIntelligence
A definition of intelligence, intended to be sufficiently concrete to support implementation efforts (i.e. Strong AI)
learn
Neuro-symbolic interpretation learning (mostly just language-learning, for now)
awesome-deeplogic
A collection of papers of neural-symbolic AI (mainly focus on NLP applications)
nerfmm
(Arxiv 2021) NeRF--: Neural Radiance Fields Without Known Camera Parameters
qagnn
QA-GNN: Question Answering using Language Models and Knowledge Graphs
BehaviorTree.CPP
Behavior Trees Library in C++. Batteries included.
opennars
OpenNARS for Research 3.0+
pyodide
The Python scientific stack, compiled to WebAssembly
gym-miniworld
Simple 3D interior simulator for RL & robotics research
nerf
Code release for NeRF (Neural Radiance Fields)
DCGAN-tensorflow
A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"
Deep_reinforcement_learning_Course
Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
silero-models
Silero Models: pre-trained STT models and benchmarks made embarrassingly simple
parglare
A pure Python scannerless LR/GLR parser - http://www.igordejanovic.net/parglare/
set.mm
Metamath source file for logic and set theory
metamath-exe
Metamath program - source code for the Metamath executable
dparser
A Scannerless GLR parser/parser generater.
awesome-deep-learning-papers
The most cited deep learning papers
PythonRobotics
Python sample codes for robotics algorithms.
minetest
Minetest, an open source infinite-world block sandbox game engine with support for survival and crafting. Also see https://github.com/minetest/minetest_game
todoist-linux
The Linux wrapper for Todoist web version
pytorch-a2c-ppo-acktr-gail
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
brat
brat rapid annotation tool (brat) - for all your textual annotation needs