Skip to content

EnvCommons/word_ladder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WordLadder

OpenReward Environment

Description

WordLadder is an environment for evaluating agents on building word ladders by changing one letter at a time to transform a start word into an end word. This environment wraps the WordLadder implementation from TextArena, a framework for text-based game environments.

Capabilities

  • Building valid word transformation sequences
  • Vocabulary knowledge and word recognition
  • Path-finding in word networks
  • Testing sequential reasoning and planning

Compute Requirements

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

License

MIT.

Tasks

There are two splits: train (450 tasks) and test (450 tasks). Each split contains 50 tasks across each of 9 variants:

  • WordLadder-v0
  • WordLadder-v0-hard
  • WordLadder-v0-hard-raw
  • WordLadder-v0-hard-train
  • WordLadder-v0-medium
  • WordLadder-v0-medium-raw
  • WordLadder-v0-medium-train
  • WordLadder-v0-raw
  • WordLadder-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:

  • submit_word(word): Submit the next word in the ladder.

Time Horizon

WordLadder is a multi-turn environment.

Environment Difficulty

Medium to Hard. Word Ladder requires vocabulary knowledge, understanding of valid English words, and path-finding through word networks. Difficulty increases with longer optimal paths.

Other Environment Requirements

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

Safety

Agents in WordLadder interact only with a word transformation 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}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors