43 projects
portal
Fast and reliable distributed systems in Python
elements
Building blocks for productive research
flexbuild
Simple Python build backend for large codebases
granular
Fast format for datasets
tinybuild
None
ninjax
Flexible Modules for JAX
scope
Metrics logging and analysis
atlas
Interactive environments for AI agents
framestack
None
videostack
None
arrange
None
cloudpath
Optimized pathlib backend for Google Cloud
twist
Fast and reliable distributed systems in Python
tensorsets
Fast format for datasets.
mindpark
Testbed for deep reinforcement learning
world-models
World models
worldmodels
World models
dreamer
Mastering Diverse Domains through World Models
dojo
World model research
zerofun
Remote function calls for array data using ZMQ
fidjax
Frechet Inception Distance in JAX.
bags
Fast format for datasets.
embodied
Fast reinforcement learning research
skybridge
Fast client and server for sending array data.
crafter
Open world survival game for reinforcement learning.
procgen-mirror
Procedurally Generated Game-Like RL Environments
procgen2
Procedurally Generated Game-Like RL Environments
diamond-env
Minecraft Diamond Env
dreamerv3
Mastering Diverse Domains through World Models
npgame
Write simple games in Numpy!
dreamerv2
Mastering Atari with Discrete World Models
imptools
Tools for improving Python imports.
pathimp
Import Python modules from any file system path.
chunkedfile
Save file writes into multiple chunks.
cowherd
Partially-observed visual reinforcement learning domain.
bridgewalk
Visual reinforcement learning benchmark for controllability.
handout
Turn Python scripts into handouts with Markdown and figures
planetrl
Open source implementation of the Deep Planning Networkreinforcement learning agent.
batch-ppo
Efficient TensorFlow implementation of reinforcement learning algorithms.
agents
Efficient TensorFlow implementation of reinforcement learning algorithms.
definitions
Load and validate YAML definitions against a schema
sets
Read datasets in a standard way.
layered
Clean reference implementation of feed forward neural networks
