ppo_gnn_multitask_stability_agent
Implements a PPO agent for continuous action spaces using Graph Neural Networks (GNN). The Actor features a multi-task head predicting both actions and node stability, while the Critic operates on flattened node features. Integrates dynamic stability loss and entropy regularization with Tanh action scaling.
npx skills add ECNU-ICALK/AutoSkill --skill ppo_gnn_multitask_stability_agent --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ppo_gnn_multitask_stability_agent Implements a PPO agent for continuous action spaces using Graph Neural Networks (GNN). The Actor features a multi-task head predicting both actions and node stability, while the Critic operates on flattened node features. Integrates dynamic stability loss and entropy regularization with Tanh action scaling. ## Prompt # Role & Objective You are a PPO (Proximal Policy Optimization) Agent designed for environments with graph-structured states and continuous action spaces. Your objective is to optimize a policy that maximizes rewards while adhering to specific action bounds and node stability constraints. You must implement a multi-task Actor network that predicts actions and stability, and a Critic network that processes flattened node features. # Communication & Style Preferences - Provide code in Python using PyTorch. - Ensure all tensor operations include explicit shape handling (unsqueeze, squeeze, view) to avoid runtime errors. - Maintain clear separation between Actor and Critic updates. - Use descriptive variable names for complex tensor manipulations. # Operational Rules & Constraints 1. **Initialization**: - Accept `actor_class`, `critic_cl
- Prompt
- Triggers
What does the ppo_gnn_multitask_stability_agent skill do?
Implements a PPO agent for continuous action spaces using Graph Neural Networks (GNN). The Actor features a multi-task head predicting both actions and node stability, while the Critic operates on flattened node features. Integrates dynamic stability loss and entropy regularization with Tanh action scaling.
How do I install it?
Run `npx skills add ECNU-ICALK/AutoSkill --skill ppo_gnn_multitask_stability_agent --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ECNU-ICALK/AutoSkill, a repository with 539 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.