SettlersOfCatan

Description

SettlersOfCatan is an environment for evaluating agents on strategic resource management and territory expansion in Settlers of Catan. This environment wraps the SettlersOfCatan implementation from TextArena, a framework for text-based game environments.

Capabilities

• Resource management and trading
• Strategic territory expansion
• Complex action planning and sequencing
• Negotiation and player interaction

Compute Requirements

SettlersOfCatan 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:

• SettlersOfCatan-v0
• SettlersOfCatan-v0-train
• SettlersOfCatan-v0-raw

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:

• take_action(action): Take an action in Settlers of Catan. Examples: [build road (0,1)-(1,0)], [build settlement (0,2)], [upgrade city (0,2)], [negotiate Player1 offer lumber:1 for brick:1], [nothing]

Time Horizon

SettlersOfCatan is a multi-turn environment.

Environment Difficulty

High. Agents must manage complex game state including resources, territory, and building strategies, while taking up to 10 actions per turn to build settlements, cities, roads, and negotiate trades with opponents to earn Victory Points.

Other Environment Requirements

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

Safety

Agents in SettlersOfCatan interact only with a board game simulation 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}
}