Nvidia nemo gym reward profiling

Skill autohandai/community-skills/nvidia-nemo-gym-reward-profiling

A collection of curated, useful, and safe skills for Autohand Code CLI Agent

Install

npx -y skills add autohandai/community-skills --skill nvidia-nemo-gym-reward-profiling

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

9 stars9 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial profiling, and rollout_infos. For failed jobs, prefer nemo-gym-debugging.

The file declares its own license as Apache-2.0 AND CC-BY-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.9 KB, as published. Nobody here has run it

Nemo Gym Reward Profiling

Invocation Check

Use this skill when the user wants to run, understand, or lightly modify Nemo Gym reward profiling. Keep the answer oriented around the normal workflow:

ng_run starts model/resource servers, ng_collect_rollouts writes rollout artifacts, and ng_reward_profile generates profiling output from those artifacts.

If the user is primarily debugging a failed job or stack trace, use the nemo-gym-debugging skill first.

Basic Workflow

Identify the environment config paths and input JSONL.
Start Gym servers with ng_run.
Collect rollouts with ng_collect_rollouts; this writes rollouts.jsonl and *_materialized_inputs.jsonl.
Run ng_reward_profile on the materialized inputs and rollout JSONL to generate *_reward_profiling.jsonl.
Inspect line counts and profile rows.

Repeated rollouts are the main profiling lever. num_repeats=1 is valid, but per-task averages and variance are only meaningful with multiple rollouts per task.

Core Concepts

*_materialized_inputs.jsonl: expanded collection inputs after repeat expansion, agent defaults, and task/rollout id assignment.
rollouts.jsonl: one completed rollout/result per materialized input row.
*_reward_profiling.jsonl: one summarized profile row per original task with at least one completed rollout.
_ng_task_index: original task/sample id.
_ng_rollout_index: repeated rollout id for that task.
rollout_infos: compact per-rollout info inside each task profile row, including reward, token usage, and numeric rollout metrics when available.

Keep reward-to-length or reward-to-token analysis keyed by both _ng_task_index and _ng_rollout_index.

Reference Loading

Load references only when the user needs that detail:

Read references/quick-start.md for a generic command template and the minimal run sequence.
Read references/output-format.md to explain materialized inputs, rollout JSONL, reward profile rows, rollout_infos, and partial profiling.

Practical Defaults

Treat ng_reward_profile as the reward profiling step; rollout collection does not write reward profile files.
Run strict profiling by default. If rollout collection stopped early, use ++allow_partial_rollouts=True to profile completed rollouts and drop original input rows with no completed rollout.
Trust the target checkout's CLI help and nemo_gym/reward_profile.py over memory if flags differ.