rlxp-propose-candidates
CommunityPropose safe next RL experiments
Software Engineering#reinforcement-learning#curriculum-learning#experiment-planning#domain-randomization#candidate-generation#reward-tuning
Authorjunhyekh
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps you choose the next reinforcement-learning experiment after analyzing results, while staying inside the active task and study contract.
Core Features & Use Cases
- Converts run analysis into bounded candidate proposals for reward tuning, curriculum, domain randomization, instrumentation repair, or reward engineering.
- Keeps proposals aligned with the current task, study, budget, and validation evidence so you do not drift out of scope.
- Use it when an experiment stalls, robustness is weak, or you need a safe hypothesis to test next.
Quick Start
Ask the assistant to propose the next contract-allowed RL experiment candidates from the latest analysis and state files.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: rlxp-propose-candidates Download link: https://github.com/junhyekh/rlxp/archive/main.zip#rlxp-propose-candidates Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 537,000+ vetted skills library on demand.