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