{
 "schema_version": 1,
 "generated": "2026-10-24",
 "id": "openmoss-openeta--run-parallel-libero-evaluation",
 "repo": "OpenMOSS/OpenETA",
 "repo_url": "https://github.com/OpenMOSS/OpenETA",
 "repo_slug": "openmoss-openeta",
 "title": "Run LIBERO episodes in parallel with human recovery",
 "page_title": "How to run LIBERO episodes in parallel with human recovery with Open ETA",
 "summary": "Execute a LIBERO manifest across ten concurrent isolated episodes and save results to JSON.",
 "who": "A research team measuring a Planner on the LIBERO task suite who needs many episodes finished in a reasonable time with isolated runs.",
 "problem": "Running LIBERO tasks one at a time is slow, and parallel runs can interfere with each other if episodes are not isolated.",
 "outcome": "The team gets outputs/parallel-libero.json with per-episode results from isolated parallel runs.",
 "steps": [
  "Run `uv sync --extra dev` and `bash scripts/setup_envs.sh libero` in the Open ETA repository folder.",
  "Run `uv run python -m sim.mcp_server` and keep it running.",
  "Run `uv run openeta-batch --manifest examples/parallel_libero_eval.json --concurrency 10 --approvement reviewed_autonomy --output outputs/parallel-libero.json`. (inferred, check the README)",
  "Review the output JSON and check each episode's trusted environment receipt before reporting a success rate."
 ],
 "agent_prompt": "In the OpenETA repo, run the parallel LIBERO evaluation with `uv run openeta-batch --manifest examples/parallel_libero_eval.json --concurrency 10 --approvement reviewed_autonomy --output outputs/parallel-libero.json`. Report the number of episodes completed and the success count backed by environment receipts, and flag any episode without a receipt.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "120 minutes",
 "basis": "readme",
 "caveat": "The README says process completion does not imply task success, so report success only from environment receipts, rewards, checkers, or retained rollout evidence.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.10 or newer and uv installed",
  "An OpenAI-compatible Planner LLM or VLM endpoint for any run that reasons over a task",
  "One simulator backend installed through scripts/setup_envs.sh, such as libero"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Ten concurrent episodes each call the Planner endpoint, so check that the API key and rate limits cover that load before starting."
  }
 ],
 "best": false,
 "score": 0.6,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/openmoss-openeta/run-parallel-libero-evaluation/",
 "md": "https://dedupedai.com/use-cases/openmoss-openeta/run-parallel-libero-evaluation/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/openmoss-openeta--run-parallel-libero-evaluation.json",
 "api_version": "v1"
}