Giters
Tim Rocktäschel (rockt)

rockt

Geek Repo

482

followers

105

following

413

stars

Company:Google DeepMind, University College London

Location:London

Home Page:rockt.github.io

Twitter:@_rockt

Github PK Tool:Github PK Tool

Organizations
ucl-dark
uclnlp
wolfe-pack

Tim Rocktäschel's starred repositories

NN-SVG

Publication-ready NN-architecture schematics.

Language:JavaScriptLicense:MITStargazers:4453Issues:60Issues:41

acme

A library of reinforcement learning components and agents

Language:PythonLicense:Apache-2.0Stargazers:3409Issues:83Issues:264

GhostText

👻 Use your text editor to write in your browser. Everything you type in the editor will be instantly updated in the browser (and vice versa).

Language:JavaScriptLicense:MITStargazers:3239Issues:37Issues:228

pytorchviz

A small package to create visualizations of PyTorch execution graphs

Language:Jupyter NotebookLicense:MITStargazers:3063Issues:31Issues:63

org-roam-ui

A graphical frontend for exploring your org-roam Zettelkasten

Language:TypeScriptLicense:GPL-3.0Stargazers:1895Issues:35Issues:212

UnicodePlots.jl

Unicode-based scientific plotting for working in the terminal

Language:JuliaLicense:NOASSERTIONStargazers:1394Issues:13Issues:147

functorch

functorch is JAX-like composable function transforms for PyTorch.

Language:Jupyter NotebookLicense:BSD-3-ClauseStargazers:1377Issues:27Issues:520

torchtyping

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

Language:PythonLicense:Apache-2.0Stargazers:1343Issues:16Issues:35

chatarena

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

Language:PythonLicense:Apache-2.0Stargazers:1271Issues:19Issues:22

tiny-differentiable-simulator

Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

Language:C++License:Apache-2.0Stargazers:1159Issues:36Issues:45

nle

The NetHack Learning Environment

Language:CLicense:NOASSERTIONStargazers:937Issues:31Issues:113

xmanager

A platform for managing machine learning experiments

Language:PythonLicense:Apache-2.0Stargazers:799Issues:30Issues:32

sample-factory

High throughput synchronous and asynchronous reinforcement learning

Language:PythonLicense:MITStargazers:761Issues:18Issues:98

minihack

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

Language:PythonLicense:Apache-2.0Stargazers:458Issues:13Issues:39

evosax

Evolution Strategies in JAX 🦎

Language:PythonLicense:Apache-2.0Stargazers:456Issues:10Issues:37

pixray

neural image generation

Language:PythonLicense:NOASSERTIONStargazers:400Issues:14Issues:40

moolib

A library for distributed ML training with PyTorch

Language:C++License:MITStargazers:365Issues:12Issues:19

crafter

Benchmarking the Spectrum of Agent Capabilities

Language:PythonLicense:MITStargazers:356Issues:9Issues:18

launchpad

Language:PythonLicense:Apache-2.0Stargazers:307Issues:19Issues:40

QDax

Accelerated Quality-Diversity

Language:PythonLicense:MITStargazers:242Issues:6Issues:63

minimax

Efficient baselines for autocurricula in JAX.

Language:PythonLicense:Apache-2.0Stargazers:145Issues:7Issues:2

gym-city

An interface with micropolis for city-building agents, packaged as an OpenAI gym environment

Language:CLicense:MITStargazers:138Issues:9Issues:9

OrgMark

Insert and edit drawing in Org mode with iPad.

Language:SwiftStargazers:97Issues:3Issues:2

einshape

Language:PythonLicense:Apache-2.0Stargazers:91Issues:8Issues:3

e3b

Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".

Language:PythonLicense:NOASSERTIONStargazers:78Issues:8Issues:3

TeachMyAgent

TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.

Language:Jupyter NotebookLicense:MITStargazers:63Issues:9Issues:5

paired

PAIRED in PyTorch 🔥

Language:PythonLicense:Apache-2.0Stargazers:55Issues:2Issues:5

Stratega

Documentation: https://stratega.readthedocs.io/en/latest/

Language:C++Stargazers:41Issues:5Issues:9

nle-language-wrapper

Nethack Learning Environment Wrapper for Language Interface

Language:PythonLicense:MITStargazers:31Issues:1Issues:3

dynabench

Dynamic Adversarial Benchmarking platform

Language:PythonLicense:MITStargazers:23Issues:18Issues:240