Demo: Open-Loop Evaluation¶
Run the standard demo plus the sample open-loop dataset workflow:
roboci demo --openloop
This command uses the sample dataset and reference model bundled with the installed package, so it works outside a repository checkout.
Equivalent standalone command:
roboci openloop run \
--dataset examples/datasets/sample_openloop \
--model examples/agents/rule_based_agent.py \
--task trajectory_prediction
The standalone command uses explicit examples/... paths and therefore requires a cloned checkout or equivalent local files.
Expected outputs:
runs/<openloop-run>/openloop/predictions.jsonlruns/<openloop-run>/openloop/per_sample_metrics.jsonlruns/<openloop-run>/openloop/aggregate_metrics.jsonruns/<openloop-run>/metrics.jsonruns/<openloop-run>/report.htmlruns/<openloop-run>/report.md
Limitations: the bundled dataset is intentionally tiny and deterministic. It is useful for artifact and metric checks, not model quality claims.