rnow-rewards

Name: rnow-rewards
Availability: InStock
Author: ReinforceNow

Design and validate reinforcement learning reward functions with ReinforceNow.

31|4|Updated Oct 8, 2025

Search Tags:#reinforcement-learning #RL #reward #RewardArgs #llm_judge #math-verify

Ready to run

npx skills add https://github.com/ReinforceNow/reinforcenow-cli --skill rnow-rewards

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rnow-rewards
Source: https://github.com/ReinforceNow/reinforcenow-cli/tree/main/project8/.claude/skills/rnow-rewards
Command: npx skills add https://github.com/ReinforceNow/reinforcenow-cli --skill rnow-rewards

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reward function design for ReinforceNow RL training can be error-prone and time-consuming. This Skill provides a structured approach to implementing and validating reward functions, including common patterns and best practices.

Core Features & Use Cases

Supports exact-match, contains, numerical tolerance, math-verify, llm_judge, and combined strategies.
Provides precondition, sandbox, and LLM-based evaluation workflows for robust reward design.
Real-world use: implement a reward to score a model's answer against a ground-truth key and gate improvements with preconditions.

Quick Start

Create rewards.py using @reward-decorated functions such as accuracy, and wire them into train.jsonl's rewards field. Install necessary dependencies, e.g., math-verify, and configure secrets if using llm_judge.

Frequently Asked Questions about rnow-rewards

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I define reinforcement learning rewards for model training?▼

To define reinforcement learning rewards, you create a rewards.py file using @reward-decorated functions and wire them into train.jsonl's rewards field. This provides a structured approach to implementing and validating reward patterns for ReinforceNow training.

What reward patterns are available for validating model outputs?▼

Available reward patterns for validating model outputs include exact matches, contain-based checks, numerical tolerance, math verification, and LLM-based judgments. You can also combine these strategies to robustly evaluate training responses.

Can I use an LLM judge to score reinforcement learning responses?▼

Yes, you can use an LLM judge to score reinforcement learning responses by configuring the llm_judge reward strategy. This requires an OpenAI API key configured as a secret to evaluate and score the model's answer.

Do I need math-verify to implement numerical tolerance rewards?▼

You need to install the math-verify dependency to implement numerical tolerance rewards and math verification workflows. This optional tool provides robust mathematical evaluation when scoring model outputs against ground-truth keys.

How do I gate reinforcement learning improvements with preconditions?▼

To gate reinforcement learning improvements with preconditions, you use the skill's precondition workflows to evaluate a model's answer before applying the reward. This ensures only valid responses pass the gate before scoring against ground-truth keys.

What is the best way to structure reward functions for ReinforceNow?▼

The best way to structure reward functions for ReinforceNow is using @reward-decorated functions like accuracy in a rewards.py file. This pattern supports sandbox execution and combined strategies for robust reward design.