Agent skill

rloo

Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Includes thinking-aware patterns.

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill rloo --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 10 KB
Bundled scripts: none
Path: skills/ai-ml/rloo/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Reinforcement Learning with Leave-One-Out (RLOO) ## Overview RLOO is a reinforcement learning method that uses leave-one-out baseline estimation for variance reduction. Like GRPO, it generates multiple completions per prompt but uses a different baseline computation that can provide more stable gradients. This skill includes patterns for training thinking/reasoning models. ## Quick Reference | Component | Purpose | |-----------|---------| | `RLOOTrainer` | RL trainer with RLOO baseline | | `RLOOConfig` | Training hyperparameters | | `reward_funcs` | Reward function(s) for scoring | | `completion_ids` | Token IDs passed to reward functions (no re-tokenization) | | `num_generations` | Completions per prompt (4 typical) | | `kl_coef` | KL penalty coefficient (0.05, lower than GRPO) | | `learning_rate` | 1e-5 (same as GRPO) | | Token ID 151668 | `</think>` boundary for Qwen3-Thinking models | ## Critical Environment Setup ```python import os from dotenv import load_dotenv load_dotenv() # Force text-based progress in Jupyter os.environ["TQDM_NOTEBOOK"] = "false" # CRITICAL: Set BEFORE importing unsloth/TRL os.environ['ACCELERATE_MIXED_PRECISION'] = 'bf16' ``` ## Critical Import Order

What's inside
Steps it walks through
  1. Overview
  2. Quick Reference
  3. Critical Environment Setup
  4. Critical Import Order
  5. RLOO Concepts
  6. How RLOO Works
  7. Leave-One-Out Baseline
  8. Comparison with GRPO
  9. Dataset Format
  10. Setup
  11. Load Model
  12. Apply LoRA
  13. RLOOTrainer Configuration
  14. Basic Configuration
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the rloo skill do?

Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Includes thinking-aware patterns.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill rloo --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 majiayu000/claude-skill-registry, a repository with 534 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.

Keep going