Jumanji

Release Notes
Environment specs are now attributes instead of methods with no arguments. Additionally, FlatPack training was broken due to a type-casting issue, which is now fixed.

What's Changed
* fix: flatpack was training with ints by sash-a in https://github.com/instadeepai/jumanji/pull/234
* docs: update readme with paper and missing GIFs by clement-bonnet in https://github.com/instadeepai/jumanji/pull/235
* feat(specs): make environment specs managed attributes by aar65537 in https://github.com/instadeepai/jumanji/pull/220
* ci: increment version to 1.0.1 by clement-bonnet in https://github.com/instadeepai/jumanji/pull/236


**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v1.0.0...v1.0.1

Jumanji v1
This release accompanies the [ICLR 2024 paper](https://openreview.net/forum?id=C4CxQmp9wc). The library now includes 22 environments!

What's Changed
* docs: fix typo in mmst.md by eltociear in https://github.com/instadeepai/jumanji/pull/178
* fix: latest chex and jax by clement-bonnet in https://github.com/instadeepai/jumanji/pull/181
* fix bugs in specs test by George-Ogden in https://github.com/instadeepai/jumanji/pull/184
* docs: fix links at top of README by George-Ogden in https://github.com/instadeepai/jumanji/pull/196
* fix(maze): fixed row and col in _compute_action_mask function. by danielpalen in https://github.com/instadeepai/jumanji/pull/194
* fix(roboticWarehouse): goal conditional by arnupretorius in https://github.com/instadeepai/jumanji/pull/191
* Tetris docs by George-Ogden in https://github.com/instadeepai/jumanji/pull/200
* fix: mention to rware in rendering code by clement-bonnet in https://github.com/instadeepai/jumanji/pull/198
* feat: Toggle logo in dark mode by callumtilbury in https://github.com/instadeepai/jumanji/pull/205
* fix: reward and discount spec not in wrapper by sash-a in https://github.com/instadeepai/jumanji/pull/206
* fix: timestep extras default value by sash-a in https://github.com/instadeepai/jumanji/pull/207
* chore: fix matplotlib and jax typing issues by sash-a in https://github.com/instadeepai/jumanji/pull/216
* Refactoring/type hints by dantp-ai in https://github.com/instadeepai/jumanji/pull/215
* Revert "feat: Toggle logo in dark mode" by callumtilbury in https://github.com/instadeepai/jumanji/pull/209
* Fix: issue in dtype of grid in cleaner env by raphaelavalos in https://github.com/instadeepai/jumanji/pull/217
* feat: pacman environment by siddarthsingh1 in https://github.com/instadeepai/jumanji/pull/186
* feat: adding sokoban environment by mvmacfarlane in https://github.com/instadeepai/jumanji/pull/185
* ci: fix tests in pipeline by clement-bonnet in https://github.com/instadeepai/jumanji/pull/225
* fix: requirements by sash-a in https://github.com/instadeepai/jumanji/pull/224
* Fix/packages data not included in sokoban by coyettev in https://github.com/instadeepai/jumanji/pull/227
* fix: autoreset wrappers by sash-a in https://github.com/instadeepai/jumanji/pull/223
* fix: default value for obs in extras by clement-bonnet in https://github.com/instadeepai/jumanji/pull/228
* feat: FlatPack environment by RuanJohn in https://github.com/instadeepai/jumanji/pull/188
* feat: implement the sliding tile puzzle env by ElshadaiK in https://github.com/instadeepai/jumanji/pull/189
* ci: increment version by clement-bonnet in https://github.com/instadeepai/jumanji/pull/230
* fix: pypi deployment by clement-bonnet in https://github.com/instadeepai/jumanji/pull/231
* ci: pypi deployment replace setuptools with hatch by clement-bonnet in https://github.com/instadeepai/jumanji/pull/232

New Contributors
* eltociear made their first contribution in https://github.com/instadeepai/jumanji/pull/178
* George-Ogden made their first contribution in https://github.com/instadeepai/jumanji/pull/184
* danielpalen made their first contribution in https://github.com/instadeepai/jumanji/pull/194
* callumtilbury made their first contribution in https://github.com/instadeepai/jumanji/pull/205
* dantp-ai made their first contribution in https://github.com/instadeepai/jumanji/pull/215
* raphaelavalos made their first contribution in https://github.com/instadeepai/jumanji/pull/217
* siddarthsingh1 made their first contribution in https://github.com/instadeepai/jumanji/pull/186
* mvmacfarlane made their first contribution in https://github.com/instadeepai/jumanji/pull/185
* RuanJohn made their first contribution in https://github.com/instadeepai/jumanji/pull/188

**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v0.3.1...v1.0.0

Release Notes
In this release, we update the dependencies to support the latest `jax` (and `chex`) version and optimize the environment speed of `Game2048`.

What's Changed
* fix(examples): port notebook to colab by clement-bonnet in https://github.com/instadeepai/jumanji/pull/169
* ci: update to latest jax and chex by clement-bonnet in https://github.com/instadeepai/jumanji/pull/174
* build: remove jaxlib by clement-bonnet in https://github.com/instadeepai/jumanji/pull/175
* docs: update readme citation by clement-bonnet in https://github.com/instadeepai/jumanji/pull/176
* feat(2048): environment performance improvements by aar65537 in https://github.com/instadeepai/jumanji/pull/172
* build: bump version to 0.3.1 by clement-bonnet in https://github.com/instadeepai/jumanji/pull/177


**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v0.3.0...v0.3.1

Update
We release `v0.3.0` with a more standardized codebase that now includes 18 environments.

What's Changed
* fix(generator_maze): correct definition of width and height by coyettev in https://github.com/instadeepai/jumanji/pull/126
* fix: make autoreset wrapper return 2 on reset by rodSiry in https://github.com/instadeepai/jumanji/pull/123
* feat(maze): update generator to return state by PDuckworth in https://github.com/instadeepai/jumanji/pull/122
* feat(connector): single agent by sash-a in https://github.com/instadeepai/jumanji/pull/119
* feat(tsp): generator by surana01 in https://github.com/instadeepai/jumanji/pull/137
* refactor(snake): define viewer outside the env class by clement-bonnet in https://github.com/instadeepai/jumanji/pull/134
* fix(training): connector num_agents in networks by clement-bonnet in https://github.com/instadeepai/jumanji/pull/145
* feat(cvrp): generator by surana01 in https://github.com/instadeepai/jumanji/pull/138
* feat(knapsack): generator by surana01 in https://github.com/instadeepai/jumanji/pull/139
* fix(parametric_action_distribution): sum kl divergence over event_ndims in parametric action distribution by clement-bonnet in https://github.com/instadeepai/jumanji/pull/142
* feat(connector): random walk board generator by mwolinska in https://github.com/instadeepai/jumanji/pull/120
* fix(2048): incorrect action mask by aar65537 in https://github.com/instadeepai/jumanji/pull/144
* fix: put upper bounds on versions of jax and jaxlib by dluo96 in https://github.com/instadeepai/jumanji/pull/150
* feat(robot_warehouse): full environment by arnupretorius in https://github.com/instadeepai/jumanji/pull/140
* feat(graph_coloring): implement graph_coloring environment by ElshadaiK in https://github.com/instadeepai/jumanji/pull/130
* feat(sudoku): implement environment by Egiob in https://github.com/instadeepai/jumanji/pull/125
* fix: data copy setup by Egiob in https://github.com/instadeepai/jumanji/pull/151
* docs: image fixes by clement-bonnet in https://github.com/instadeepai/jumanji/pull/154
* feat(MMST): multi minimum spanning tree environment by ulricharmel in https://github.com/instadeepai/jumanji/pull/135
* feat(multi_cvrp): Implement MultiCVRP environment by DriesSmit in https://github.com/instadeepai/jumanji/pull/133
* feat(tetris): implement Tetris environment by MedAliMimouni in https://github.com/instadeepai/jumanji/pull/132
* fix: jax version constraint by aar65537 in https://github.com/instadeepai/jumanji/pull/160
* feat: paper configs by clement-bonnet in https://github.com/instadeepai/jumanji/pull/156
* docs: update online doc with new environments by clement-bonnet in https://github.com/instadeepai/jumanji/pull/158
* feat(training): multi-worker training by clement-bonnet in https://github.com/instadeepai/jumanji/pull/164
* feat(training): upload checkpoints by clement-bonnet in https://github.com/instadeepai/jumanji/pull/165
* ci: increment version by clement-bonnet in https://github.com/instadeepai/jumanji/pull/167

New Contributors
* rodSiry made their first contribution in https://github.com/instadeepai/jumanji/pull/123
* PDuckworth made their first contribution in https://github.com/instadeepai/jumanji/pull/122
* sash-a made their first contribution in https://github.com/instadeepai/jumanji/pull/119
* mwolinska made their first contribution in https://github.com/instadeepai/jumanji/pull/120
* Uokoroafor made their first contribution in https://github.com/instadeepai/jumanji/pull/120
* RandyBrown1965 made their first contribution in https://github.com/instadeepai/jumanji/pull/120
* ojorgensen made their first contribution in https://github.com/instadeepai/jumanji/pull/120
* baubels made their first contribution in https://github.com/instadeepai/jumanji/pull/120
* aar65537 made their first contribution in https://github.com/instadeepai/jumanji/pull/144
* arnupretorius made their first contribution in https://github.com/instadeepai/jumanji/pull/140
* ElshadaiK made their first contribution in https://github.com/instadeepai/jumanji/pull/130
* Egiob made their first contribution in https://github.com/instadeepai/jumanji/pull/125
* ulricharmel made their first contribution in https://github.com/instadeepai/jumanji/pull/135
* DriesSmit made their first contribution in https://github.com/instadeepai/jumanji/pull/133
* MedAliMimouni made their first contribution in https://github.com/instadeepai/jumanji/pull/132

**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v0.2.2...v0.3.0

Release Notes
This release proposes a few fixes including a standardized viewer and generator interface for Minesweeper and RubiksCube.

What's Changed
* docs(contributing): state to fork the repo to contribute by clement-bonnet in https://github.com/instadeepai/jumanji/pull/84
* docs: typo in terminal logger by clement-bonnet in https://github.com/instadeepai/jumanji/pull/105
* feat: create viewer interface for rendering of environments by dluo96 in https://github.com/instadeepai/jumanji/pull/99
* docs: add pgx to readme by clement-bonnet in https://github.com/instadeepai/jumanji/pull/108
* refactor(train): remove env factory by dluo96 in https://github.com/instadeepai/jumanji/pull/110
* feat: separate rendering and instance generation for the RubiksCube environment by TristanKalloniatis in https://github.com/instadeepai/jumanji/pull/82
* test: consistent naming in Cleaner, Maze, Game2048, and Minesweeper by dluo96 in https://github.com/instadeepai/jumanji/pull/112
* refactor(cleaner): return state from instance generator by coyettev in https://github.com/instadeepai/jumanji/pull/87
* feat: allow custom rendering and instance generation methods for Minesweeper by TristanKalloniatis in https://github.com/instadeepai/jumanji/pull/85
* ci: increment version by clement-bonnet in https://github.com/instadeepai/jumanji/pull/118

New Contributors
* TristanKalloniatis made their first contribution in https://github.com/instadeepai/jumanji/pull/82
* coyettev made their first contribution in https://github.com/instadeepai/jumanji/pull/87

**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v0.2.1...v0.2.2

Release Notes
This major release introduces a whole set of new environments, namely:
- `Game2048`: the classic 4x4 2048 game
- `Minesweeper`: the classic game from the video game
- `RubiksCube`: the standard puzzle
- `JobShop`: job-shop scheduling problem as another canonical CO problem
- `Cleaner`: a maze with multiple _agents_ that spawn across the grid in order to clean all the tiles ASAP
- `Connector`: replacement of the previous `Routing` environment reimplemented for better efficiency and modularity.
- `Maze`: classic maze on a grid

This release also stabilizes the API with a cleaner definition of the environment specs, rendering implemented for all the environments (using matplotlib), and an actor-critic agent implement for training alongside environment-specific actor-critic networks for each environment.

What's Changed
* fix: pygame requirements by wang-r-j in https://github.com/instadeepai/jumanji/pull/72
* feat: internal update for v0.2.0 by clement-bonnet in https://github.com/instadeepai/jumanji/pull/73
* refactor: remove connect4 environment
* feat: implement training and environment-specific networks in jumanji.training by clement-bonnet
* feat: replace routing environment with connector by sash-a
* feat: implement rubiks_cube environment by TristanKalloniatis
* feat: implement game_2048 environment by OmaymaMahjoub
* feat: implement minesweeper environment by TristanKalloniatis
* feat: implement job_shop environment by dluo96
* refactor: knapsack, cvrp and tsp by surana01
* feat: implement cleaner environment by coyettev
* feat: implement maze environment by PDuckworth
* feat: clean and augment snake with action mask by clement-bonnet
* refactor: implement arbitrarily nested specs by dluo96
* ci: drop support for python 3.7

New Contributors
* wang-r-j made their first contribution in https://github.com/instadeepai/jumanji/pull/72

**Full Changelog**: https://github.com/instadeepai/jumanji/compare/v0.1.6...v0.2.1