QuantumTicTacToe

API Endpoint
Leaderboard
Loading leaderboard...
README

QuantumTicTacToe

OpenReward Environment

Description

QuantumTicTacToe is an environment for evaluating agents on a quantum variant of tic-tac-toe where marks exist in superposition. This environment wraps the QuantumTicTacToe implementation from TextArena, a framework for text-based game environments.

Capabilities

  • Quantum-inspired reasoning with superposition states
  • Complex state tracking across multiple positions
  • Strategic planning with entangled game states
  • Two-player competitive gameplay against an LLM opponent

Compute Requirements

QuantumTicTacToe 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:

  • QuantumTicTacToe-v0
  • QuantumTicTacToe-v0-train
  • QuantumTicTacToe-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:

  • place_mark(position_a, position_b): Place a quantum mark in two different cells (0-8)

Time Horizon

QuantumTicTacToe is a multi-turn environment.

Environment Difficulty

Hard. Quantum TicTacToe adds significant complexity to standard tic-tac-toe through quantum superposition, requiring agents to track multiple potential board states and anticipate collapse scenarios.

Other Environment Requirements

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

Safety

Agents in QuantumTicTacToe interact only with a board 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}
}
GeneralReasoning/QuantumTicTacToe | OpenReward