-
-
dreamerv3 Public
Mastering Diverse Domains through World Models
-
ninjax Public
General Modules for JAX
-
elements Public
Building blocks for productive research
-
mujoco_playground Public
Forked from google-deepmind/mujoco_playgroundAn open-source library for GPU-accelerated robot learning and sim-to-real transfer.
-
AMO Public
Forked from OpenTeleVision/AMO[RSS 2025] AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control
-
portal Public
Fast and reliable distributed systems in Python
-
-
jax Public
Forked from jax-ml/jaxComposable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Python Apache License 2.0 UpdatedMar 5, 2025 -
granular Public
Fast dataset format and loader
-
cloudpath Public
Extend pathlib to GCS, S3, HDFS via TensorFlow's GFile
-
embodied Public
Fast reinforcement learning research
-
acme Public
Forked from google-deepmind/acmeA library of reinforcement learning components and agents
Python Apache License 2.0 UpdatedSep 10, 2024 -
-
tdmpc2 Public
Forked from nicklashansen/tdmpc2Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"
-
teleport Public
Efficiently send large arrays across machines
-
fidjax Public
Frechet Inception Distance in JAX
-
bigym Public
Forked from chernyadev/bigymDemo-Driven Mobile Bi-Manual Manipulation Benchmark.
-
rich Public
Forked from Textualize/richRich is a Python library for rich text and beautiful formatting in the terminal.
Python MIT License UpdatedJun 20, 2024 -
crafter Public
Benchmarking the Spectrum of Agent Capabilities
-
lab Public
Forked from google-deepmind/labA customisable 3D platform for agent-based AI research
C Other UpdatedNov 3, 2023 -
-
mujoco Public
Forked from google-deepmind/mujocoMulti-Joint dynamics with Contact. A general purpose physics simulator.
C++ Apache License 2.0 UpdatedAug 18, 2023 -
diamond_env Public
Standardized Minecraft Diamond Environment for Reinforcement Learning
-
dreamerv2 Public
Mastering Atari with Discrete World Models
-
director Public
Deep Hierarchical Planning from Pixels
-
daydreamer Public
DayDreamer: World Models for Physical Robot Learning
-
memory-maze Public
Forked from jurgisp/memory-mazeMemory Maze environment for evaluating long-term memory of RL agents.
Python MIT License UpdatedOct 24, 2022 -
-
{{ message }}