tatsubori

Metric-FF

Metric-FF is a domain independent planning system developed by Joerg Hoffmann.

pddl-lib

A PDDL library that parse PDDL files and provides a very simple interface to interact with domain-problems.

AMR-CSLogic

A service that parses a sentence using AMR and returns a set of Verbnet logic predicates grounded with the roles of the input sentence.

audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Baselines-ETCI2021

Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training

Deep-RL-Keras

Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)

DILP-Core

Python and TensorFlow implementation of the paper "Learning Explanatory Rules from Noisy Data." Evans Richard and Edward Grefenstette. Journal of Artificial Intelligence Research 61 (2018): 1-64.

GATA-public

gym-2dcraft

gym-minigrid

Minimalistic gridworld package for OpenAI Gym

lab-agile-planning

LOA

Logical Optimal Action (LOA), a novel RL with Logical Neural Network (LNN) on text-based games

NLRL

Source code of Neural Logic Reinforcement Learning (https://arxiv.org/abs/1904.10729)

onsets-and-frames

A Pytorch implementation of Onsets and Frames (Hawthorne 2018)

pddlgym

Convert a PDDL domain into an OpenAI Gym environment.

PyTorchSR

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution

rddl2tf_tf2

RDDL2TensorFlow compiler.

rddlgym_tf2

A toolkit for working with RDDL domains in Python3.

rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

rl-baselines3-zoo

A collection of pre-trained RL agents using Stable Baselines3, training and hyperparameter optimization included.

rl-testbed-for-energyplus

Reinforcement Learning Testbed for Power Consumption Optimization using EnergyPlus

s3fs

S3 Filesystem

SubGen

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

torchgeo

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

UQ-climate-impact-benchmarking

A Surrogate Model Benchmark for Dynamic Climate Impact Models

visual-hints-textworld-rl

Visual Hints in Textworld Cooking Game for Multi-modal RL

watson-python-sdk

:snake: Client library to use the IBM Watson services in Python and available in pip as watson-developer-cloud

YOLOV3-Keras