rl-reward
提供可配置奖励策略与对比式方案，便于训练回报设计
为 RL/RLHF 构造点式或对式奖励并聚合多维评分为标量
帮你为 RL/RLHF 构造奖励信号，能在 pointwise 与 pairwise 策略间选型，并把多维评分聚合成训练用的标量。适合做奖励模型、为 GRPO/REINFORCE 打分、生成 DPO 的偏好对或做 Best-of-N 选择。会处理归一化、净胜率等细节，兼顾算法效率与训练稳定性。
▸ 展开 SKILL.md 英文原文
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.
帮我安装这个 skill：https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/rl-reward/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/agentscope-ai/OpenJudge/main/skills/rl-reward/SKILL.md"# 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, structu