IndianPoker

Description

IndianPoker is an environment for evaluating agents on poker strategy with imperfect information. This environment wraps the IndianPoker implementation from TextArena, a framework for text-based game environments.

Capabilities

• Betting strategy with incomplete information
• Bluffing and deception in poker scenarios
• Risk management and pot odds calculation
• Competitive gameplay against an LLM opponent

Compute Requirements

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

License

MIT.

Tasks

There are two splits: train (750 tasks) and test (750 tasks). Each split contains 50 tasks across each of 15 variants:

• IndianPoker-v0-short
• IndianPoker-v0-short-train
• IndianPoker-v0-short-raw
• IndianPoker-v0
• IndianPoker-v0-train
• IndianPoker-v0-raw
• IndianPoker-v0-medium
• IndianPoker-v0-medium-train
• IndianPoker-v0-medium-raw
• IndianPoker-v0-long
• IndianPoker-v0-long-train
• IndianPoker-v0-long-raw
• IndianPoker-v0-extreme
• IndianPoker-v0-extreme-train
• IndianPoker-v0-extreme-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 five tools:

• check(params): Check (pass without betting). Only valid when no bet is active.
• bet(amount): Open betting with the specified amount.
• call_bet(params): Call (match) the current bet.
• raise_bet(amount): Raise the current bet by the specified amount.
• fold(params): Fold your hand and give up the current pot.

Time Horizon

IndianPoker is a multi-turn environment.

Environment Difficulty

Medium-Hard - requires probabilistic reasoning under uncertainty, strategic betting decisions, and the ability to infer opponent strategy from betting patterns while only seeing their card.

Other Environment Requirements

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

Safety

Agents in IndianPoker interact only with a poker 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}
}