git
ask
hub
Privacy
Terms
Sign in with GitHub
suz-tsinghua/smp
↗
Stars ·
215
Language ·
Python
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: suz-tsinghua
Ask anything about this repo to start.
Explain how the motion prior model guides the reinforcement learning policy in this SMP reproduction.
Walk me through training the walk-forward task using the included pretrained motion prior checkpoint.
How does multiplying the task and motion rewards instead of adding them change what the policy learns?
Help me set up mjlab and uv to run this project's simulation environment.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).