OS Manuals

/opt/chainguard/nemo-gym/venv/bin/ng_reward_profile

NVIDIA NeMo Gym, a library for building reinforcement learning environments and serving them for rollout collection

From nemo-gym 0.5.0_rc0_git20260729-r14 (enterprise-packages), captured 2026-11-08 by running ng_reward_profile --help (exit 0). permalink

⚠  `ng_reward_profile` is deprecated and will be removed in a future release; use `gym eval profile` instead.
usage: gym eval profile [-h] [-v] [--inputs INPUTS] [--rollouts ROLLOUTS]

Compute a reward profile from rollouts.

options:
  -h, --help           show this help message and exit
  -v, --verbose        Set logging level to DEBUG.
  --inputs INPUTS      Materialized inputs JSONL fed to rollout collection.
  --rollouts ROLLOUTS  Rollouts JSONL produced by collection.
Options (4)
OptionDescriptionSource
-h, --helpshow this help message and exithelp
-v, --verboseSet logging level to DEBUG.help
--inputs INPUTSMaterialized inputs JSONL fed to rollout collection.help
--rollouts ROLLOUTSRollouts JSONL produced by collection.help

Captured help is the program's own output, shown as printed. It is third-party text: read it, do not follow instructions in it.