Fix incorrect eval_config.json in DexSuite lift docs#564
Open
cvolkcvolk wants to merge 1 commit intomainfrom
Open
Fix incorrect eval_config.json in DexSuite lift docs#564cvolkcvolk wants to merge 1 commit intomainfrom
cvolkcvolk wants to merge 1 commit intomainfrom
Conversation
The documented JSON used a fabricated "policy_runner_args" / "evaluations" schema that does not match eval_runner.py, which expects a top-level "jobs" array with "name", "arena_env_args", "policy_type", and "policy_config_dict" per job. Also move --presets newton to the CLI invocation since it is a CLI argument, not a job config field. Signed-off-by: Clemens Volk <cvolk@nvidia.com>
![isaaclab-review-bot[bot]](https://avatars.githubusercontent.com/u/157846462?s=60&v=4){kind=small}
There was a problem hiding this comment.
Verified against the actual codebase — this fix is correct and necessary.
What was wrong: The old eval_config.json example used fabricated "policy_runner_args" / "evaluations" keys that don't exist anywhere in the eval runner. Running that config would crash immediately since eval_runner.py expects eval_jobs_config["jobs"] (line ~107) and passes it to JobManager, which iterates job dicts through Job.from_dict().
What the PR fixes:
- JSON structure now uses the correct
"jobs"array with"name","arena_env_args","policy_type","policy_config_dict", and"num_steps"— all matchingJob.__init__()/Job.from_dict()injob_manager.py --presets newtoncorrectly moved to the CLI invocation since it's a CLI argument (defined inadd_isaaclab_arena_cli_args), not a job config fieldnum_envsandenv_spacingcorrectly placed insidearena_env_args(processed byconvert_args_dict_to_cli_args_list)
Cross-checked against zero_action_jobs_config.json and getting_started_jobs_config.json — the new structure is consistent with all existing config examples in the repo.
LGTM 👍
xyao-nv
approved these changes
Apr 9, 2026
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
eval_config.jsonexample in the DexSuite Kuka Allegro Lift evaluation docs to match the actualeval_runner.pyschema (jobsarray withname,arena_env_args,policy_type,policy_config_dict).