New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: implement the sliding tile puzzle env #189

Merged

djbyrne merged 54 commits into instadeepai:main from ElshadaiK:feat/add_sliding_tile_puzzle_environment

Mar 14, 2024

Contributor

ElshadaiK commented Jul 18, 2023

Details:
Implements the full SlidingTilePuzzle environment with actor-critic and random networks as well as documentation.

Notes:
Gifs are still to be updated. Training of an a2c agent is ongoing

sash-a requested changes

View reviewed changes

Collaborator

sash-a left a comment

This looks really great! Couple minor changes and we got to wait and see how well it performs 🔥

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/__init__.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env_test.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

clement-bonnet requested changes

View reviewed changes

Collaborator

clement-bonnet left a comment

Thank you for the PR! Left a few comments on a first review :)

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

carlosgmartin commented Nov 2, 2023

What's the status of this PR? Anything I could help with?

sash-a previously approved these changes

View reviewed changes

Collaborator

sash-a left a comment

Sorry this took so long, but awesome work @ElshadaiK I think it's pretty much ready just some minor comments from my side

jumanji/environments/logic/sliding_tile_puzzle/env.py Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

jumanji/environments/logic/sliding_tile_puzzle/reward.py Outdated Show resolved Hide resolved

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

ElshadaiK dismissed sash-a’s stale review via

4b6770b

January 16, 2024 17:43

clement-bonnet reviewed

View reviewed changes

docs/environments/sliding_tile_puzzle.md Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/constants.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/env.py Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/env.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/generator.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/reward.py Outdated Show resolved Hide resolved

clement-bonnet reviewed

View reviewed changes

Collaborator

clement-bonnet left a comment

LGTM overall, still investigating why training doesn't work.

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/types.py Show resolved Hide resolved

clement-bonnet force-pushed the feat/add_sliding_tile_puzzle_environment branch from 0284549 to 72af3fe Compare

March 12, 2024 14:27

sash-a requested changes

View reviewed changes

Collaborator

sash-a left a comment

Just some small things we need to add here. Also need to add this mkdocs.yaml and add the gif

jumanji/environments/logic/sliding_tile_puzzle/env.py Show resolved Hide resolved

docs/environments/sliding_tile_puzzle.md Outdated Show resolved Hide resolved

jumanji/training/configs/config.yaml Outdated Show resolved Hide resolved

jumanji/training/configs/config.yaml Outdated Show resolved Hide resolved

ElshadaiK and others added 13 commits

March 13, 2024 18:38


          feat: implement the sliding tile puzzle env

74b4a8f


          exp: sliding tiles with a2c first run

2883f60


          fix: bug fix

9c41355


          Update jumanji/environments/logic/sliding_tile_puzzle/generator.py

233b0ea

Co-authored-by: Sasha <[email protected]>


          Update jumanji/environments/logic/sliding_tile_puzzle/generator.py

02e812c

Co-authored-by: Sasha <[email protected]>


          Update jumanji/environments/logic/sliding_tile_puzzle/env_test.py

9e12bd7

Co-authored-by: Sasha <[email protected]>


          fix: address PR reviews on var naming & unused method

165f897


          Update jumanji/environments/logic/sliding_tile_puzzle/env.py

8b58328

Co-authored-by: Clément Bonnet <[email protected]>


          fix: address issues on doc

d16187e


          fix: make reward external

d0f0fb5


          Update jumanji/environments/logic/sliding_tile_puzzle/env.py

cd2c047

Co-authored-by: Sasha <[email protected]>


          Update jumanji/environments/logic/sliding_tile_puzzle/env.py

f8b65b9

Co-authored-by: Sasha <[email protected]>


          Update jumanji/environments/logic/sliding_tile_puzzle/env.py

cb2a1c3

Co-authored-by: Sasha <[email protected]>

ElshadaiK and others added 13 commits

March 13, 2024 18:39


          fix: update how solved puzzle is computed

7d6da94


          merge

a8c404d


          feat: a2c works on 3x3

a1c220c


          fix: init import

dc1ecf8


          refactor: clem clean PR

616ef6f


          chore: update stp grid size

0defaee


          feat: deafult behavior wrappers

84a4fe8


          fix: linter

c425c59


          fix: linters

37f8d40


          chore: update train config

75480a2


          docs: add step count to obs


          fix: viewer

1bec548


          feat: sliding tile puzzle gif

00d6980

clement-bonnet force-pushed the feat/add_sliding_tile_puzzle_environment branch from 5acc203 to 00d6980 Compare

March 13, 2024 17:40

clement-bonnet reviewed

View reviewed changes

jumanji/environments/logic/sliding_tile_puzzle/reward.py Outdated Show resolved Hide resolved

clement-bonnet and others added 2 commits

March 13, 2024 18:47


          docs: mkdocs

e84f6ab


          Apply suggestions from code review

bd4f0bf

Co-authored-by: Sasha <[email protected]>

clement-bonnet previously approved these changes

View reviewed changes


          fix: isort

fb58be4

clement-bonnet dismissed their stale review via

fb58be4

March 13, 2024 18:13

clement-bonnet previously approved these changes

View reviewed changes

sash-a previously approved these changes

View reviewed changes


          fix: tests

b492701

clement-bonnet dismissed stale reviews from sash-a and themself via

b492701

March 13, 2024 20:21

clement-bonnet previously approved these changes

View reviewed changes

Collaborator

clement-bonnet left a comment

LGTM


          fix: sokoban generator fixture

56975ec

clement-bonnet dismissed their stale review via

56975ec

March 14, 2024 09:15

clement-bonnet approved these changes

View reviewed changes

djbyrne merged commit a903c4f into instadeepai:main

3 checks passed

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