Skip to content

Conversation

@layterz
Copy link

@layterz layterz commented Nov 24, 2025

Adds a simple new lock_key environment. This is basically an extension of squared, but where the agent needs to first collect n keys before reaching the goal square. Additionally, the agent can only observe state within a range from its current position. Keys are green; locks are red and the agent is cyan. Control the number of keys with --env.num-keys 5, grid size with --env.size 11, and observation range with --env.obs-dist 2

This is very basic - I built this to get a better feel for the library - so feel free to close if this isn't useful.

output

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant