# 02-rl-reward

> Build RL reward signals using the OpenJudge framework.

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.

- Type: Skill
- Made by: agentscope-ai
- Category: AI & agents
- Formats: Skills
- Version: 0eb5c48
- Source: https://github.com/agentscope-ai/openjudge/tree/HEAD/skills/openjudge-core/02-rl-reward
- Page: https://pluginboard.ai/skills/02-rl-reward

## Works with

- ChatGPT
- Claude
- Gemini
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT: Download the 02-rl-reward folder and zip it, then Plugins → Skills → Create → Upload from your computer. Business and Enterprise plans.

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Claude

In Claude (web or desktop): Download the 02-rl-reward folder and zip the folder itself, then upload it in Customize → Skills.

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Gemini

In Gemini: Download the 02-rl-reward folder, then at gemini.google.com click Customize → Skills → Create → Upload and pick the folder (or a .zip of it).

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### GitHub Copilot

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.copilot/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Cursor

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.cursor/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Claude Code

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.claude/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Codex

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.agents/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Antigravity

In Antigravity: Copy the 02-rl-reward folder into ~/.gemini/config/skills (Antigravity app and IDE) or ~/.gemini/antigravity-cli/skills (Antigravity CLI).

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Gemini CLI

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.gemini/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Replit

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward .agents/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### OpenClaw

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.openclaw/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### OpenCode

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.config/opencode/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

### Hermes Agent

Run in your terminal:

```shell
npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.hermes/skills/02-rl-reward
```

View the folder on GitHub: https://github.com/agentscope-ai/OpenJudge/tree/HEAD/skills/openjudge-core/02-rl-reward

---
From Pluginboard (https://pluginboard.ai).
