rl-reward
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
Profile →npx skills add agentscope-ai/OpenJudge --skill rl-reward --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.
# RL Reward Construction with OpenJudge Build reward signals for reinforcement learning from human feedback (RLHF) and reinforcement learning from AI feedback (RLAIF) using the `openjudge` library. ## When to Use This Skill - Building scalar rewards for GRPO / REINFORCE rollout scoring - Generating (chosen, rejected) preference pairs for DPO / IPO - Best-of-N candidate selection - Multi-dimensional reward shaping (correctness + safety + format) - Replacing or bootstrapping a reward model with LLM-as-judge ## Step 1 — Choose Your Reward Strategy Use this decision tree **before** writing any code: ``` RL Algorithm + Task type? │ ├── GRPO / REINFORCE — Verifiable task (math, code, structured output) │ └── → POINTWISE ✅ (FunctionGrader, exact score, zero LLM cost) │ ├── GRPO / REINFORCE — Subjective task (instruction following, dialogue, summarization) │ └── → PAIRWISE TOURNAMENT ✅ (compare each rollout vs all others in group, │ reward = net win rate within group) │ ├── DPO / IPO / SLiC — need (chosen, rejected) pairs │ └── → PAIRWISE ✅ (two-way comparison, return winner/loser) │ └── Best-of-N / reranking — rank N candidates └── → LISTWISE ✅ (single call ranks all N at once) ``` ``` Co
- When to Use This Skill
- Step 1 — Choose Your Reward Strategy
- Sub-documents — Read When Relevant
- Install
- Strategy Comparison
- Score Normalization
- Evaluation Strategies
- Choose Your Strategy
- Pointwise — Noise Reduction with Voting / Average
- Pairwise — GRPO Tournament
pip install py-openjudge
What does the rl-reward skill do?
Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
How do I install it?
Run `npx skills add agentscope-ai/OpenJudge --skill rl-reward --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 agentscope-ai/OpenJudge, a repository with 764 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.