sparkmind 2.0.0rc1

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
# Core package
pip install -e .

# AWS/LIBERO training image equivalent extras
pip install -e ".[aws]"

Optional extras include aws, libero, aloha, pusht, envs, pi, and dev.

docs/lerobot_commands.md