# Nvidia Nemo Gym Gym > Nemo Gym Reward Profiling - Skill: `tomevault-io/nvidia-nemo-gym-gym` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/nvidia-nemo-gym-gym` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/nvidia-nemo-gym-gym/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/nvidia-nemo-gym-gym --- # 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: `gym env start` starts model/resources servers, `gym eval run --no-serve` writes rollout artifacts, and `gym eval 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 1. Identify the environment config paths and input JSONL. 2. Start Gym servers with `gym env start`. 3. Collect rollouts with `gym eval run --no-serve`; this writes `rollouts.jsonl` and `*_materialized_inputs.jsonl`. 4. Run `gym eval profile` on the materialized inputs and rollout JSONL to generate `*_reward_profiling.jsonl`. 5. 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 `gym eval 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. --- > Source: [NVIDIA-NeMo/Gym](https://github.com/NVIDIA-NeMo/Gym) — distributed by [TomeVault](https://tomevault.io).