sparkmind 1.0.0rc1

Unified Robot Skill Learning Framework

SparkMind

Unified robot skill learning on top of Hydra, LeRobot, and (for RL) Isaac Gym / RofuncRL-style stacks. Training scripts live under examples/.

---

Supported algorithms

Area	Algorithm / model
IL imitation learning	ACT (Action Chunking Transformer)
	Diffusion policy
RL reinforcement learning	Humanoid AMP (RofuncRL, Isaac Gym)
	HOTU (skill transfer, RofuncRL)
	HOTU (view / motion)
	HumanGPT (humanoid imitation, RofuncRL)
VLA vision–language–action	SmolVLA
	XVLA
	π₀ (PI0)
	π₀.₅ (PI05)
	GR00T
	Wall-X

---

Installation

Requirements: Python 3.12, pip, and a clone of this repository.

cd /path/to/SparkMind
# pip install -e . 
pip install -e ".[all]" # install all extras

Optional simulation suites and VLA policy extras (e.g. envs, pi, xvla, all) are documented here:

docs/Installation.md

Docker build and runtime usage for the current IL / VLA image is documented here:

docs/DOCKER_USAGE_ZH.md