JeyRunner
Follow
🔍 rob-research
A framework for Reinforcement Learning research.
A differentiable physics engine and multibody dynamics library for control and robot learning.
Package for generation of symbolic (SX) expressions of robot kinematics and dynamics. Based on URDF and Pinocchio.
Jiminy: a fast and portable Python/C++ simulator of poly-articulated robots with OpenAI Gym interface for reinforcement learning
A CasADi Python wrapper for the acados integrators.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A framework for writing and solving optimization problem, with an emphasis on robotic control (Beta)
Optax is a gradient processing and optimization library for JAX.
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
A logger, server and visualization dashboard for ML projects
Open source platform for the machine learning lifecycle
Differentiable Rasteriser implemented in JAX. Reference: https://github.com/erwincoumans/tinyrenderer, https://github.com/ssloy/tinyrenderer/wiki; PR: https://github.com/google/brax/pull/367
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/
⚡ Flashbax: Accelerated Replay Buffers in JAX
Really Fast End-to-End Jax RL Implementations
Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
A JAX research toolkit for building, editing, and visualizing neural networks.
Orbax provides common checkpointing and persistence utilities for JAX users
🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation
Oryx is a library for probabilistic programming and deep learning built on top of Jax.
Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.