{"data":{"kind":"file","path":"README.md","version_id":"m4afh6itnqoiz4dn1t4b0fb3","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1670,"modified_at":"2025-10-24T20:50:59.021000","content_hash":"5467aa156a979702717c962856f907bfa47b0de3384454e5760aad2cf54eb59f"},"entries":[],"content":"# sudoku\n\n### Overview\n- **Environment ID**: `sudoku`\n- **Short description**: Sudoku puzzle-solving environment using TextArena\n- **Tags**: train, eval\n\n### Datasets\n- **Primary dataset(s)**: TextArena Sudoku game dataset\n- **Source links**: TextArena framework\n- **Split sizes**: 2000 train / 20 eval (configurable)\n\n### Task\n- **Type**: multi-turn\n- **Parser**: XMLParser with `<guess>...</guess>` tags\n- **Rubric overview**: \n  - `check_answer_reward_func`: Exact match accuracy (1.0 or 0.0)\n  - `partial_credit_reward_func`: Partial credit based on correct cells (0-1.0)\n  - `count_turns_reward_func`: Efficiency reward (correct answer divided by turns taken)\n  - Format reward (weight: 0.2)\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval sudoku\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval sudoku \\\n  -m gpt-4.1-mini \\\n  -n 20 -r 3 -t 1024 -T 0.7 \\\n  -a '{\"num_eval_examples\": 50}'\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.\n\n### Environment Arguments\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `num_train_examples` | int | `2000` | Number of training examples |\n| `num_eval_examples` | int | `20` | Number of evaluation examples |\n\n### Metrics\n\n| Metric | Meaning |\n| ------ | ------- |\n| `check_answer_reward_func` | Binary reward: 1.0 for exact match, 0.0 otherwise |\n| `partial_credit_reward_func` | Partial credit based on number of correct cells (0-1.0) |\n| `count_turns_reward_func` | Efficiency metric: accuracy divided by (number of turns + 1) |\n| `format_reward` | Reward for following the required XML format |\n","encoding":"utf-8","truncated":false,"total_bytes":1670},"status":null}