{"data":{"kind":"file","path":"README.md","version_id":"az0qcoa9y4h9ecxubl9p8w81","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1115,"modified_at":"2025-09-13T05:38:49.664000","content_hash":"3caf716901f4de253545570945a9236e5821ded8fc83b28607d1d67b2b108691"},"entries":[],"content":"# TicTacToe\n\nThis environment functions as both an environment and a benchmark for LLM's to play chess against a minmax function of TicTacToe.\nCurrently, version 0.1, the agent will play as X.\n\n### Overview\n- **Environment ID**: `TicTacToe_env`\n- **Short description**: Simulates a TicTacToe game versus a minmax function.\n- **Tags**: eval, TicTacToe\n\n### Datasets\n- **Primary dataset(s)**: No dataset, starting from empty positions\n\n### Task\n- **Type**: multi-turn\n- **Parser**: custom\n- **Rubric overview**: outcome_reward. Since if played perfectly a TicTacToe game will always end in a draw, we reward any outcome that isnt the environment winning\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval TicTacToe\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval TicTacToe   -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\n### Metrics\n\n| Metric | Meaning |\n| ------ | ------- |\n| `reward` | Rewards, the closer to 0 the worse |","encoding":"utf-8","truncated":false,"total_bytes":1115},"status":null}