catastrophic-forgetting

Testing environment for various ideas to overcome the catastrophic forgetting.

compressai

A PyTorch library and evaluation platform for end-to-end compression research

cosmos

Algorithms that run our universe | Your personal library of every algorithm and data structure code that you will ever encounter

differentiable-hard-attention-module

A modified version of Spatial Transformer Networks to attend regions on the input image.

empiric-rl

Standardize benchmarking package of some Reinforcement Learning environments.

graph-dqn

Unofficial pytorch implementation of Graph-DQN

graph-warehouse

Reinforcement Learning experiments with graphs on warehouse environment

gym-doom

Gym - Doom environments based on VizDoom.

gymcolab

Gym-like pycolab environments

hashdrone

jaxdp

A Dynamic Programming package for discrete MDPs implemented in JAX

lamp

Logging and Monitoring Package. Python logging for data visualization, mostly based on Pytorch.

modular-baselines

A modular Reinforcement Research framework based on Stable-Baselines3

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

offlinerlviaio

pycolab

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch_scatter

PyTorch Extension Library of Optimized Scatter Operations

rl_pysc2

DRL algorithms for Starcraft II

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

stable-baselines3

PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.

tensorforce

TensorForce: A TensorFlow library for applied reinforcement learning

tolgaok

Config files for my GitHub profile.

tolgaok.github.io

ur_gym

A reinforcement learning ready gazebo environment with Universal Robot 10. Similar to gym API.

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.