Briscola

Description

Briscola is an ORS environment for evaluating agents on playing Briscola, an Italian trick-taking card game, against an LLM opponent. This environment wraps the Briscola implementation from TextArena, a framework for text-based game environments.

Capabilities

• Strategic card game reasoning with trick-taking mechanics
• Value-based decision making (Ace=11, Three=10, King=4, Queen=3, Jack=2)
• Trump suit recognition and tactical play
• Competitive two-player gameplay against an LLM opponent

Compute Requirements

Briscola 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:

• Briscola-v0
• Briscola-v0-train
• Briscola-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:

• play_card(card_number): Play a card from your hand by its number (1-indexed).

Time Horizon

Briscola is a multi-turn environment.

Environment Difficulty

Medium

Other Environment Requirements

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

Safety

Agents in Briscola interact only with a card 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}
}