LinesOfAction

Description

LinesOfAction is an environment for evaluating agents on the abstract strategy board game where players connect their pieces into a single group. This environment wraps the LinesOfAction implementation from TextArena, a framework for text-based game environments.

Capabilities

• Abstract strategic planning and spatial reasoning
• Long-term tactical positioning
• Geometric and topological thinking about board connectivity
• Two-player competitive gameplay against an LLM opponent

Compute Requirements

LinesOfAction does not require a sandbox. It has minimal compute requirements.

License

MIT.

Tasks

There are two splits: train (150 tasks) and test (150 tasks). Each split contains 50 tasks across each of 3 variants:

• LinesOfAction-v0
• LinesOfAction-v0-raw
• LinesOfAction-v0-train

Each task is seeded for reproducibility.

Reward Structure

This is a sparse reward environment. Rewards are mapped from TextArena's native range of {-1, 0, 1} to {0.0, 0.5, 1.0} via (raw + 1) / 2.

We do not use LLM graders for this environment; reward is determined programmatically.

Data

Game state is generated procedurally by the TextArena engine using seeded randomness. No external data files are required.

Tools

Agents are given a single tool:

• move_piece(from_square, to_square): Move a piece from one square to another using algebraic notation (e.g., 'a1' to 'a3').

Time Horizon

LinesOfAction is a multi-turn environment.

Environment Difficulty

Hard. Lines of Action requires advanced spatial reasoning, the ability to predict opponent moves, and strategic planning to connect pieces while preventing the opponent from doing the same.

Other Environment Requirements

This environment requires an OpenAI API key (passed via secrets) to power the LLM opponent.

Safety

Agents in LinesOfAction interact only with a board game and have no access to external systems, the internet, or sensitive data. The environment does not present safety risks.

Citations

@software{textarena2024,
  author    = {Guertler, Leon and Banting, Wilfried and Pignatelli, Eduardo},
  title     = {TextArena},
  year      = {2024},
  publisher = {GitHub},
  url       = {https://github.com/LeonGuertler/TextArena}
}