mknbv

raps

Code for the paper "Causal Bandits without Graph Learning"

compressed-transformer

Compression of NMT transformer model with tensor methods

adashift

AdaShift optimizer implementation in PyTorch

cleangpt

CleanGPT — a clean ground up re-implementation of LLMs

derl

derl is a DEep Reinforcement Learning package

meta

Code for COLT'22 paper "Trace norm regularization for multi-task learning with scarce data"

neuralode-rl

Neural Ordinary Differential Equations for Reinforcement Learning

rl

rljs

Tabular reinforcement learning methods in JavaScript

zamburak

Bandit algorithms in OCaml

mknbv/neuralode-rl

Neural Ordinary Differential Equations for Reinforcement Learning

mknbv/adashift

AdaShift optimizer implementation in PyTorch

mknbv/derl

derl is a DEep Reinforcement Learning package

mknbv/rl

mknbv/zamburak

Bandit algorithms in OCaml

mknbv/cleangpt

CleanGPT — a clean ground up re-implementation of LLMs

mknbv/meta

Code for COLT'22 paper "Trace norm regularization for multi-task learning with scarce data"

mknbv/rljs

Tabular reinforcement learning methods in JavaScript

mknbv/awesome-polars

A curated list of Polars talks, tools, examples & articles. Contributions welcome !

mknbv/higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

mknbv/iclr_2019

ICLR Reproducibility Challenge 2019

mknbv/jellybeans.vim

A colorful, dark color scheme for Vim.

mknbv/u4ml

Utilities for machine learning

mknbv/vim-airline-themes

A collection of themes for vim-airline