{"data":{"kind":"file","path":"README.md","version_id":"ssa78qt4y2t3f7c37yxk3v2v","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":2491,"modified_at":"2025-08-19T22:27:48.353000","content_hash":"ed5aeaa448d3011f7d85f3e1696e4db6fbabeb7c413fcbfd5a539e6f52a590a2"},"entries":[],"content":"# jericho\n\n\nVerifiers friendly wrapper around the Jericho learning environment for interactive fiction games.\nSee the upstream project: [Jericho learning environment](https://github.com/microsoft/jericho).\n\nMore games as environments coming soon. Learn more @ [4Wall AI](https://www.4wallai.com).\n\n## TODO\n- [ ] Complete readme\n- [ ] Clean up env\n- [ ] Rubric documentation\n- [ ] Eval all games\n\n### Overview\n- **Environment ID**: `jericho-text-adventures`\n- **Short description**: Learning environment for interactive fiction games (based on jericho).\n- **Tags**: <multi-turn>, <games>\n\n### Datasets\n- **Primary dataset(s)**: <name(s) and brief description>\n- **Source links**: <links>\n- **Split sizes**: <train/eval counts>\n\n### Task\n- **Type**: multi-turn\n- **Parser**: <e.g., ThinkParser, XMLParser, custom>\n- **Rubric overview**: <briefly list reward functions and key metrics>\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval jericho\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval jericho   -m gpt-4.1-mini   -n 20 -r 3 -t 1024 -T 0.7   -a '{\"key\": \"value\"}'  # env-specific args as JSON\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.\n- Reports are written under `./environments/jericho/reports/` and auto-embedded below.\n\n### Environment Arguments\nDocument any supported environment arguments and their meaning. Example:\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `foo` | str | `\"bar\"` | What this controls |\n| `max_examples` | int | `-1` | Limit on dataset size (use -1 for all) |\n\n### Metrics\nSummarize key metrics your rubric emits and how they’re interpreted.\n\n| Metric | Meaning |\n| ------ | ------- |\n| `reward` | Main scalar reward (weighted sum of criteria) |\n| `accuracy` | Exact match on target answer |\n\n## Evaluation Reports\n\n<!-- Do not edit below this line. Content is auto-generated. -->\n<!-- vf:begin:reports -->\n<p>No reports found. Run <code>uv run vf-eval jericho -a '{\"key\": \"value\"}'</code> to generate one.</p>\n<!-- vf:end:reports -->\n\n## Citation\n\n```bibtex\n@article{hausknecht19,\n  title={Interactive Fiction Games: A Colossal Adventure},\n  author={Hausknecht, Matthew and Ammanabrolu, Prithviraj and C\\^ot\\'{e} Marc-Alexandre and Yuan Xingdi},\n  journal={CoRR},\n  year={2019},\n  url={http://arxiv.org/abs/1909.05398},\n  volume={abs/1909.05398}\n}\n```\n\nJericho repo: [microsoft/jericho](https://github.com/microsoft/jericho)\n","encoding":"utf-8","truncated":false,"total_bytes":2491},"status":null}