Michael Laskin (MishaLaskin)

MishaLaskin

Geek Repo

Company:DeepMind

Location:New York City

Home Page:https://www.mishalaskin.com/

Twitter:@MishaLaskin

Github PK Tool:Github PK Tool

Michael Laskin's starred repositories

ring-flash-attention

Ring attention implementation with flash attention

Language:PythonStargazers:390Issues:0Issues:0

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Language:PythonLicense:Apache-2.0Stargazers:497Issues:0Issues:0

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Language:PythonLicense:Apache-2.0Stargazers:10794Issues:0Issues:0
Language:TypeScriptStargazers:291Issues:0Issues:0

weblm

Drive a browser with Cohere

Language:PythonLicense:MITStargazers:73Issues:0Issues:0

zsh_codex

This is a ZSH plugin that enables you to use OpenAI's Codex AI in the command line.

Language:PythonLicense:MITStargazers:1340Issues:0Issues:0

emoji-semantic-search

Search the most relevant emojis given a natural language query

Language:PythonStargazers:239Issues:0Issues:0

cic

CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery

Language:PythonStargazers:78Issues:0Issues:0

geometry-dex

PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"

Language:PythonLicense:MITStargazers:55Issues:0Issues:0

TD3_BC

Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

Language:PythonLicense:MITStargazers:295Issues:0Issues:0
Language:PythonLicense:MITStargazers:322Issues:0Issues:0

ibc

A PyTorch implementation of Implicit Behavioral Cloning

Language:PythonStargazers:93Issues:0Issues:0
Language:PythonLicense:MITStargazers:212Issues:0Issues:0

ppo-ewma

Code for the paper "Batch size invariance for policy optimization"

Language:Jupyter NotebookLicense:MITStargazers:48Issues:0Issues:0

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:718Issues:0Issues:0

triton

Development repository for the Triton language and compiler

Language:C++License:MITStargazers:11666Issues:0Issues:0

drqv2

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Language:PythonLicense:MITStargazers:332Issues:0Issues:0

alphafold

Open source code for AlphaFold.

Language:PythonLicense:Apache-2.0Stargazers:12006Issues:0Issues:0

RE3

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

Language:Jupyter NotebookStargazers:62Issues:0Issues:0

colabgymrender

Render OpenAI Gym environments in Google Colaboratory

Language:Jupyter NotebookLicense:MITStargazers:56Issues:0Issues:0

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Language:PythonLicense:MITStargazers:2215Issues:0Issues:0

android_env

RL research on Android devices.

Language:PythonLicense:Apache-2.0Stargazers:967Issues:0Issues:0

ant-design

An enterprise-class UI design language and React UI library

Language:TypeScriptLicense:MITStargazers:90702Issues:0Issues:0

Andrew-Ng-Machine-Learning-Notes

The offical notes of Andrew Ng Machine Learning in Stanford University

Stargazers:273Issues:0Issues:0

mbrl-lib

Library for Model Based RL

Language:PythonLicense:MITStargazers:928Issues:0Issues:0

minimal_goexplore

A minimal implementation of Go-Explore without domain knowledge

Language:PythonLicense:MITStargazers:13Issues:0Issues:0
Language:Jupyter NotebookLicense:MITStargazers:79Issues:0Issues:0

fairchem

FAIR Chemistry's library of machine learning methods for chemistry

Language:PythonLicense:NOASSERTIONStargazers:694Issues:0Issues:0

CovidPrognosis

COVID deterioration prediction based on chest X-ray radiographs via MoCo-trained image representations

Language:PythonLicense:MITStargazers:157Issues:0Issues:0

flare

Reinforcement Learning with Latent Flow

Language:PythonLicense:MITStargazers:41Issues:0Issues:0