Improve prompt to make it complete Sokoban level 1 #32
Conversation
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
- swap row_index and col_index so that it is easy for understanding - refine definiton of tiles in matrix - define clear actions(up/down/left/right) - add multiple steps example
- Put 'thought' before 'action' in output foramt. Hope this make the 'thought' process leads to accurate 'action' instead of adjustiying action ahead.
- add restart and remove actions
- replace default levels file with the one from https://github.com/morenod/sokoban/blob/master/levels - add 'levels_filename' and 'max_leve' arguments to sokoban game
- Make AI output one move/thought at one time. It looks multiple steps in one output make things worse in complicated level. - Add '+'(worker on dock). This is necessary since it make AI be aware of dock even there is a worker on it.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
As I experiments, I found that the "brief reasoning" in Sokoban agent prompt would make LLM output less thinking and hard to get a working strategy.
So I updated the prompt and get it complete level 1 in one shot. The log is as this https://gist.github.com/mocheng/17b6a2d0d63fcaf26238e9e2dbf42c10#file-gistfile1-txt .