Port NetHack Sokoban

[BartekCupial]

NetHack Sokoban

Introduction

I have added 8 Sokoban levels to the MiniHack based on the dat file from NLE. These levels are challenging and have solutions available in the NetHack Wiki, making them useful for research on combining external knowledge to learn strategies for NetHack.

Changes to Original NetHack Sokoban Levels

• All "wholes" have been changed into pits.
• Falling into a pit results in the agent's death.
• There are no monsters or items in any of the levels, including 4a and 4b Sokoban levels, which normally spawn a zoo filled with monsters.
• All doors are closed, but none are locked.

Reward shaping and termination

The environment is completed when all pits are filled and the agent steps on the stairs down.
The agent receives a +1 reward for finishing the episode and a +0.1 reward for filling each pit.

[facebook-github-bot]

Hi @BartekCupial!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[samvelyan]

Hi @BartekCupial. Many thanks for this wonderful PR. Could you please sign the Facebook CLA above so that we can proceed?

[BartekCupial]

I've already done it. Not sure why it is not checked.

[BartekCupial]

@samvelyan CLA is signed now, but I see that there is a test on macos that failed. I don't have access to this kind of hardware. Can you help?

[samvelyan]

LGTM

[samvelyan]

Tests pass now. Thank you very much for your contribution @BartekCupial