IteratedRockPaperScissors

Description

IteratedRockPaperScissors is an environment for evaluating agents on pattern recognition and strategic play in the classic hand game. This environment wraps the IteratedRockPaperScissors implementation from TextArena, a framework for text-based game environments.

Capabilities

• Pattern recognition and exploitation
• Mixed strategy development
• Adaptive play based on opponent history
• Competitive gameplay against an LLM opponent

Compute Requirements

IteratedRockPaperScissors 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:

• IteratedRockPaperScissors-v0
• IteratedRockPaperScissors-v0-train
• IteratedRockPaperScissors-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_move(move): Play rock, paper, or scissors for this round.

Time Horizon

IteratedRockPaperScissors is a multi-turn environment.

Environment Difficulty

Easy-Medium - requires understanding of cyclic dominance relationships and the ability to identify and exploit patterns in opponent play while maintaining unpredictability.

Other Environment Requirements

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

Safety

Agents in IteratedRockPaperScissors interact only with a 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}
}