TowerOfHanoi

Description

TowerOfHanoi is an environment for evaluating agents on solving the classic Tower of Hanoi puzzle with varying difficulty levels. This environment wraps the TowerOfHanoi implementation from TextArena, a framework for text-based game environments.

Capabilities

• Solving Tower of Hanoi puzzles with different numbers of disks
• Planning optimal or near-optimal move sequences
• Understanding and respecting game constraints
• Testing recursive and iterative problem-solving strategies

Compute Requirements

TowerOfHanoi 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:

• TowerOfHanoi-v0
• TowerOfHanoi-v0-extreme
• TowerOfHanoi-v0-extreme-raw
• TowerOfHanoi-v0-extreme-train
• TowerOfHanoi-v0-hard
• TowerOfHanoi-v0-hard-raw
• TowerOfHanoi-v0-hard-train
• TowerOfHanoi-v0-hardcore
• TowerOfHanoi-v0-hardcore-raw
• TowerOfHanoi-v0-hardcore-train
• TowerOfHanoi-v0-medium
• TowerOfHanoi-v0-medium-raw
• TowerOfHanoi-v0-medium-train
• TowerOfHanoi-v0-raw
• TowerOfHanoi-v0-train

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:

• move_disk(source, target): Move the top disk from source peg to target peg. Pegs are A, B, or C.

Time Horizon

TowerOfHanoi is a multi-turn environment.

Environment Difficulty

Medium to Very Hard. Tower of Hanoi requires planning, recursion understanding, and optimal move sequencing. Difficulty increases significantly with more disks (exponential growth in optimal solution length).

Other Environment Requirements

There are no further environment requirements; TowerOfHanoi works out of the box without any secrets or API keys.

Safety

Agents in TowerOfHanoi interact only with a mathematical puzzle 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}
}