Ivan Nazarov's repositories
cplxmodule
Complex-valued neural networks for pytorch and Variational Dropout for real and complex layers.
my-fair-bnb
A bare-bones scipy-based solver for mixed integer LPs
nle_toolbox
Tools, wrappers, and bots for the NLE.
gymDiscoMaze
Implementation of DiscoMaze environment from sec. 4.1 of arxiv:2002.06038
scikit-learn
Support Vector Data Description PR (branch `svdd_l1`) for scikit-learn
crossing_paper2017
An unfinished conference paper outlining the experimental results obtained in my course project in 2015.
arxiv-sanity-preserver
Web interface for browsing, search and filtering recent arxiv submissions
attention-learn-to-route
Attention based model for learning to solve different routing problems
cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
dreamerv2
Mastering Atari with Discrete World Models
ecole
Nodesel dynamics for Extensible Combinatorial Optimization Learning Environments
gym
A toolkit for developing and comparing reinforcement learning algorithms.
minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
minihack
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
never-give-up
PyTorch implementation of Never Give Up: Learning Directed Exploration Strategies
pytorch-lightning
The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
telegram-bot
A work-in-progress basic telegram bot.