Meta-World

Normalizer

Meta-World — metrics, requirements, and run commands.

Last updated: Jul 11, 2026

On this page

About Metrics Task YAML Primary Environment setup Runtime environment Evaluation data Checkpoints & assets Key environment variables Verify setup Run Evaluation Set Candidate Artifacts Import Official Results Score Generated Artifacts Direct In-Tree Runner Requirements Inputs Environment Outputs

About

Meta-World external benchmark task manifest for continuous-control manipulation rollouts.

Metrics

Meta-World external benchmark task manifest for continuous-control manipulation rollouts.

Task YAML

worldfoundry/data/benchmarks/tasks/external/metaworld.yaml

Primary

success_rate

Metric	Focus
`success_rate`	Share of episodes or tasks that complete successfully.
`task_success`	Share of episodes or tasks that complete successfully.
`reward`	Environment reward signal across Meta-World MT50/MLxx meta-RL manipulation skill episodes.
`normalized_return`	Meta-World return scaled to expert performance bounds on the evaluated task suite.

Environment setup

Runtime environment

Conda env: worldplay-core.
Separate setup: this benchmark expects a dedicated conda env rather than the unified runtime.
Meta-World/MuJoCo 官方运行环境未在当前 checkout 中就绪；需要独立 mujoco/metaworld env 后再做 suite mapping。

Evaluation data

Meta-World evaluates continuous-control manipulation policies in simulator; result JSON/CSV files are normalized by WorldFoundry.
Candidate model outputs: set WORLDFOUNDRY_METAWORLD_RESULTS_PATH to the generated-video or rollout artifact root.

Checkpoints & assets

This benchmark is primarily rollout- or official-result-driven; see catalog requires and the task YAML for policy/simulator checkpoints.

Key environment variables

WORLDFOUNDRY_METAWORLD_ROOT
WORLDFOUNDRY_METAWORLD_RESULTS_PATH

Verify setup

PYTHONPATH=. ${WORLDFOUNDRY_CONDA_ROOT}/worldplay/bin/python -m worldfoundry.evaluation.tasks.execution.orchestration.runtime_preflight --profile metaworld --manifest worldfoundry/data/benchmarks/runtime_profiles/official/metaworld.yaml --output-dir tmp/worldfoundry_preflight/metaworld --json

Run Evaluation

After preparing the assets and candidate artifacts listed on this page, use the public run entry points below.

Set Candidate Artifacts

export WORLDFOUNDRY_GENERATED_ARTIFACT_DIR=/path/to/generated/artifacts

Import Official Results

worldfoundry-eval zoo benchmark-run \
  --benchmark-id metaworld \
  --mode normalizer \
  --official-results-path /path/to/official/results-or-report \
  --generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
  --output-dir tmp/metaworld/normalizer \
  --json

Score Generated Artifacts

worldfoundry-eval zoo benchmark-run \
  --benchmark-id metaworld \
  --mode official-run \
  --generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
  --output-dir tmp/metaworld/official-run \
  --json

Direct In-Tree Runner

worldfoundry-eval zoo benchmark-run --benchmark-id metaworld --mode official-validation --official-results-path <official_results.json> --output-dir <out> --json