docs: add environment concepts pages#1265
Open
cwing-nvidia wants to merge 6 commits intomainfrom
Open
Conversation
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
… index Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…ironment definition to README - Add Evaluation concept page with model eval vs. agent eval and what makes a good eval - Restructure concepts index: rename titles (Environments, Evaluation, Agent Harness Optimization, Training) - Merge training-approaches into upcoming Training page (delete old file, add redirect) - Add environment definition to README - Update cross-links in core-components, training-tutorials index Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com> Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…ne evaluation and environments pages Add training.mdx (merged from environments-for-training + training-approaches) covering post-training techniques (SFT, RL, GRPO/DAPO/GSPO) and how environments are used for training. Add agent-harness-optimization.mdx. Update environments.mdx heading to "Anatomy of an Environment". Refine evaluation goal/description. Update index cards. Replace ASCII diagram with env-training-library image. Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…ions Add consistent Next Steps sections using Cards format across all four concept pages. Standardize card descriptions, remove inline tutorial link from training.mdx, update evaluation goal/description to match page content, fix agent-harness-optimization to link to eval concept page instead of tutorials. Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…diagram Wrap Goal + read-first links in <Info> component across concept pages for consistent styling with tutorials. Add "Read first" links to evaluation and training pages. Update model-vs-agent-eval.png with newer version. Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
cwing-nvidia
force-pushed
the
cwing/environment-docs
branch
from
556dd06 to
77dbb13
Compare
Move agent harness optimization concept page to a separate branch (cwing/agent-harness-optimization-docs) for further research. Remove all card links and Next Steps references to the page. Signed-off-by: Chris Wing <cwing@nvidia.com> Co-authored-by: Cursor <cursoragent@cursor.com>
bxyu-nvidia
reviewed
May 11, 2026
| @@ -4,6 +4,8 @@ | |||
|
|
|||
| NeMo Gym is a library for evaluating and improving models and agents using environments. NeMo Gym provides infrastructure to develop environments, scalably run evaluation and training, and a collection of popular benchmarks and training environments. | |||
Contributor
There was a problem hiding this comment.
should we also mention nemotron here?
Contributor
Author
There was a problem hiding this comment.
I mentioned Nemotron in "What NeMo Gym Provides" - do you think it needs to be mentioned here too?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
training-approaches→training<Info>component for Goal + Read First,<Cards>for Next StepsTest plan
fern checkpasses/latest/about/concepts/training-approachesworks