0

GameOfPureStrategy

Fresh

GameOfPureStrategy is an environment for evaluating agents on strategic card play in a two-player competitive game. This environment wraps the GameOfPureStrategy implementation from TextArena, a framework for text-based game environments.

Type
RL Env
Publisher
General Reasoning
Tags
Decision Making in Games
Runtime
TextArena
License
unknown
Size
300 tasks
Published
Mar 2026
Canonical
openreward.ai/GeneralReasoning/GameOfPureStrategy

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →

GameOfPureStrategy

OpenReward Environment

Description

GameOfPureStrategy is an ORS environment for evaluating agents on strategic card play in a two-player competitive game. This environment wraps the GameOfPureStrategy implementation from TextArena, a framework for text-based game environments.

Capabilities

  • Strategic decision-making with complete information
  • Resource management across multiple rounds
  • Competitive gameplay against an LLM opponent
  • Sequential card play requiring foresight and planning

Compute Requirements

GameOfPureStrategy 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:

  • GameOfPureStrategy-v0
  • GameOfPureStrategy-v0-train
  • GameOfPureStrategy-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): Play a card from your hand. Card must be one of: A, 2-10, J, Q, K.

Time Horizon

GameOfPureStrategy is a multi-turn environment.

Environment Difficulty

Medium - requires strategic planning across 13 rounds of card play, balancing short-term gains with long-term resource management.

Other Environment Requirements

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

Safety

Agents in GameOfPureStrategy interact only with a card 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}
}