Jumanji v1.0.1

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 #234
• docs: update readme with paper and missing GIFs by @clement-bonnet in #235
• feat(specs): make environment specs managed attributes by @aar65537 in #220
• ci: increment version to 1.0.1 by @clement-bonnet in #236

Full Changelog: v1.0.0...v1.0.1

Jumanji v1.0.0

Jumanji v1

This release accompanies the ICLR 2024 paper. The library now includes 22 environments!

What's Changed

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

New Contributors

• @eltociear made their first contribution in #178
• @George-Ogden made their first contribution in #184
• @danielpalen made their first contribution in #194
• @callumtilbury made their first contribution in #205
• @dantp-ai made their first contribution in #215
• @raphaelavalos made their first contribution in #217
• @siddarthsingh1 made their first contribution in #186
• @mvmacfarlane made their first contribution in #185
• @RuanJohn made their first contribution in #188

Full Changelog: v0.3.1...v1.0.0

Jumanji v0.3.1

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 #169
• ci: update to latest jax and chex by @clement-bonnet in #174
• build: remove jaxlib by @clement-bonnet in #175
• docs: update readme citation by @clement-bonnet in #176
• feat(2048): environment performance improvements by @aar65537 in #172
• build: bump version to 0.3.1 by @clement-bonnet in #177

Full Changelog: v0.3.0...v0.3.1

Jumanji v0.3.0

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

New Contributors

• @rodSiry made their first contribution in #123
• @PDuckworth made their first contribution in #122
• @sash-a made their first contribution in #119
• @mwolinska made their first contribution in #120
• @Uokoroafor made their first contribution in #120
• @RandyBrown1965 made their first contribution in #120
• @ojorgensen made their first contribution in #120
• @baubels made their first contribution in #120
• @aar65537 made their first contribution in #144
• @arnupretorius made their first contribution in #140
• @ElshadaiK made their first contribution in #130
• @Egiob made their first contribution in #125
• @ulricharmel made their first contribution in #135
• @DriesSmit made their first contribution in #133
• @MedAliMimouni made their first contribution in #132

Full Changelog: v0.2.2...v0.3.0

Jumanji v0.2.2

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 #84
• docs: typo in terminal logger by @clement-bonnet in #105
• feat: create viewer interface for rendering of environments by @dluo96 in #99
• docs: add pgx to readme by @clement-bonnet in #108
• refactor(train): remove env factory by @dluo96 in #110
• feat: separate rendering and instance generation for the RubiksCube environment by @TristanKalloniatis in #82
• test: consistent naming in Cleaner, Maze, Game2048, and Minesweeper by @dluo96 in #112
• refactor(cleaner): return state from instance generator by @coyettev in #87
• feat: allow custom rendering and instance generation methods for Minesweeper by @TristanKalloniatis in #85
• ci: increment version by @clement-bonnet in #118

New Contributors

• @TristanKalloniatis made their first contribution in #82
• @coyettev made their first contribution in #87

Full Changelog: v0.2.1...v0.2.2

Jumanji v0.2.1

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 #72
• feat: internal update for v0.2.0 by @clement-bonnet in #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 #72

Full Changelog: v0.1.6...v0.2.1

Jumanji v0.1.6

Release Notes

This release fixes the previous release (v0.1.5) that is broken on PyPi. Users may now run pip install -U jumanji or pip install jumanji==0.1.6 in replacement of pip install jumanji==0.1.5 (that is broken).

What's Changed

• refactor: remove brax by @clement-bonnet in #69
• build: increment semantic release by @clement-bonnet in #70

Full Changelog: v0.1.5...v0.1.6

Jumanji v0.1.5

What's Changed

• feat: deprecate Connect4 by @clement-bonnet in #67
• feat: increment semantic release by @clement-bonnet in #68

Full Changelog: v0.1.4...v0.1.5

Jumanji v0.1.4

What's Changed

• fix: import protocol from typing extensions to ensure Python 3.7 compatibility by @dluo96 in #59
• ci: added python 3.7 to github actions by @dluo96 in #58
• fix: solve flake8 error causing ci to fail by @dluo96 in #64
• refactor: binpack instantiation of instance generator by @cyprienc in #61
• build: increment semantic version to 0.1.4 by @clement-bonnet in #65

New Contributors

• @cyprienc made their first contribution in #61

Full Changelog: v0.1.3...v0.1.4

Jumanji v0.1.3

Release Notes

In this release, we fixed the registration of the CVRP environment.

What's Changed

• fix: import cvrp for environment registration by @clement-bonnet in #52
• build: increment semantic version to 0.1.3 by @clement-bonnet in #53

Full Changelog: v0.1.2...v0.1.3