# SimplerEnv (/docs/evaluation/benchmark-hub/simpler-env)



## About [#about]

SimplerEnv provides simulation-based embodied evaluation for real-to-sim policy testing and task-success mapping.

## Metrics [#metrics]

SimplerEnv external benchmark task manifest for simulator-backed VLA policy rollouts.

### Task YAML [#task-yaml]

`worldfoundry/data/benchmarks/tasks/external/simpler-env.yaml`

### Primary [#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.                                    |
| `episode_success` | Share of episodes or tasks that complete successfully.                                    |
| `reward`          | Real-to-sim bridge reward on SimplerEnv visual-matching manipulation evaluation episodes. |

## Environment setup [#environment-setup]

### Runtime environment [#runtime-environment]

* **Conda env:** `giga-world-policy-py311`.
* **Separate setup:** defaults to the unified WorldFoundry env (`needs_new_env: false`); a benchmark-only conda env is usually not required.
* SimplerEnv source/runtime import 可见；完整状态需要 embodiment assets、policy wrapper 和 rollout 结果。

### Evaluation data [#evaluation-data]

* SimplerEnv evaluates policy rollouts in simulator; generated result files and rollout logs are normalized by WorldFoundry.
* Candidate model outputs: set `WORLDFOUNDRY_SIMPLERENV_RESULTS_PATH` to the generated-video or rollout artifact root.
* `${WORLDFOUNDRY_CACHE_DIR}/repos/simpler-env--SimplerEnv`

### Checkpoints & assets [#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 [#key-environment-variables]

* `WORLDFOUNDRY_SIMPLERENV_ROOT`
* `WORLDFOUNDRY_SIMPLERENV_RESULTS_PATH`

### Verify setup [#verify-setup]

```bash
PYTHONPATH=${WORLDFOUNDRY_CACHE_DIR}/repos/simpler-env--SimplerEnv:src ${WORLDFOUNDRY_CONDA_ENVS_ROOT}/worldfoundry-giga-world-policy-py311/bin/python -m worldfoundry.evaluation.tasks.execution.orchestration.runtime_preflight --profile simpler-env --manifest worldfoundry/data/benchmarks/runtime_profiles/official/simpler-env.yaml --output-dir tmp/worldfoundry_preflight/simpler-env --json
```

## Run Evaluation [#run-evaluation]

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

### Set Candidate Artifacts [#set-candidate-artifacts]

```bash
export WORLDFOUNDRY_GENERATED_ARTIFACT_DIR=/path/to/generated/artifacts
```

### Import Official Results [#import-official-results]

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

### Score Generated Artifacts [#score-generated-artifacts]

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

### Direct In-Tree Runner [#direct-in-tree-runner]

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

## Requirements [#requirements]

### Inputs [#inputs]

* Official SimplerEnv repository checkout
* ManiSkill2/SAPIEN simulator stack
* Selected robot embodiment assets
* Benchmark-specific policy checkpoint

### Environment [#environment]

* `WORLDFOUNDRY_SIMPLERENV_RESULTS_PATH`

### Outputs [#outputs]

* `scorecard.json`
* `raw_results.jsonl`

[← Benchmark Hub](/docs/evaluation/benchmark-hub)