Four rooms 4#555
Open
paulmerceur wants to merge 8 commits intoPufferAI:4.0from
Open
Conversation
Copy the Four Rooms native environment sources and config from the old pufferlib-v3 fork into the v4 layout. This is an intentionally unadapted checkpoint; follow-up commits will update it for the current v4 APIs and build system.
Update Four Rooms for the v4 static vecenv interface: binding metadata, float action/terminal buffers, per-env RNG, and v4 config keys. Remove the old v3 Python wrapper because v4 integrates native Ocean environments through build.sh and config files.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a native Ocean implementation of MiniGrid Four Rooms.
Four Rooms is a simple sparse-reward navigation task with partial egocentric observations. The agent must navigate through connected rooms to reach a randomly placed goal. This implementation follows the MiniGrid action space, observation encoding, reward shaping, and wall-gap generation where practical, while keeping the native env configurable by map size.
Original environment: https://minigrid.farama.org/environments/minigrid/FourRoomsEnv/
I initially prototyped this in an older PufferLib fork and ported it to v4 for this PR. Feedback welcome.