Minigrid

In this release, we added support for Gymnasium 1.0.0 and NumPy 2.0.0+ and made many bug fixes.

New Features

- Allow custom goal colors by m-barker in https://github.com/Farama-Foundation/Minigrid/pull/451
- Added support of Gymnasium to 1.0.0 and NumPy to 2.0.0+ by BolunDai0216 in https://github.com/Farama-Foundation/Minigrid/pull/453

Bug Fixes

- Fixed the issue when generating non-square DoorKey environments by rbankosegger in https://github.com/Farama-Foundation/Minigrid/pull/429
- Fixed the documentation `env-id` parameter by turbotimon in https://github.com/Farama-Foundation/Minigrid/pull/430
- Corrected the registered configuration for UnlockPickupEnv by MarcSpeckmann in https://github.com/Farama-Foundation/Minigrid/pull/437
- Fixed`FlatObsWrapper` observation `dtype` by pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Minigrid/pull/435
- Swapped the width and height in RGBImgObsWrapper catanzaromj in https://github.com/Farama-Foundation/Minigrid/pull/445

Contributors

This release includes contributions from VioIchigo, rbankosegger, turbotimon, SimonOuellette35, MarcSpeckmann, pseudo-rnd-thoughts, RaghuSpaceRajan, jysdoran, BolunDai0216, catanzaromj, m-barker

In this release, we added new procedurally generated environments using the wave function collapse environment, the original BabyAI bot, and dynamically determined `highlighting` in `RGBImgObsWrapper`.

New Features

* Added procedural generation of environments using the [Wave Function Collapse algorithm](https://github.com/mxgmn/WaveFunctionCollapse) (adapted from [this python implementation](https://github.com/ikarth/wfc_2019f)). By jysdoran in https://github.com/Farama-Foundation/Minigrid/pull/371
* Changes the `observation` method of `RGBImgObsWrapper` such that the agent field-of-view (FOV) highlight is rendered only when the underlying environment has this enabled with the `highlight` bool, by default is True. By thesofakillers in https://github.com/Farama-Foundation/Minigrid/pull/388
* Added the BabyAI bot from the original BabyAI repo: https://github.com/mila-iqia/babyai/blob/master/babyai/bot.py
This bot can be used to generate expert demonstrations in all BabyAI environments. By thesofakillers in https://github.com/Farama-Foundation/Minigrid/pull/381

Contributors
This release includes contributions from thesofakillers, pseudo-rnd-thoughts, BolunDai0216, mansicer, JupiLogy, AdamJelley, timoklein, jysdoran, mschweizer, and Camel-light.

This release includes two new features:

- Added a new wrapper that prevents death in states like obstacles or lava, and gives an optional negative reward instead by sparisi in 374
- Added a tutorial on how to train RL agent on Minigrid environments by BolunDai0216 in 379

Contributors

This release includes contributions from: mgoulao, ertsiger, BolunDai0216, sparisi, elliottower.

New release with a couple of small changes that shouldn't affect users along with a new tutorial and python 3.11 support. Let us know if anything new breaks

Breaking changes
* Fix unintended observation space "image" size change in DictObservationWrapper by jbloomAus in https://github.com/Farama-Foundation/Minigrid/pull/345
* Fix assertion error message in Grid.set() by drmeerkat in https://github.com/Farama-Foundation/Minigrid/pull/347

New Features
* Added Tutorial for Environment Creation by BolunDai0216 in https://github.com/Farama-Foundation/Minigrid/pull/348
* Added a stochastic action wrapper by BolunDai0216 in https://github.com/Farama-Foundation/Minigrid/pull/355
* Adds python 3.11 support and updates pygame to 2.4.0 by pseudo-rnd-thoughts in https://github.com/Farama-Foundation/Minigrid/pull/361

Documentation changes
* Update home page to use new style, add view code sphinx extension, update copyright and improve SEO by mgoulao in https://github.com/Farama-Foundation/Minigrid/pull/352
* Adds DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards (U-Tokyo, Google Brain, IJCAI 2023) in publications by alpc104 in https://github.com/Farama-Foundation/Minigrid/pull/350
* Adds "Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning" by Alver and Precup, CoLLAs 2023 to publications by alversafa in https://github.com/Farama-Foundation/Minigrid/pull/359

**Full Changelog**: https://github.com/Farama-Foundation/Minigrid/compare/v2.2.1...v2.3.0

This release is a minor bugfix:
- Change the default screen size from 1 to 640 by BolunDai0216 in https://github.com/Farama-Foundation/Minigrid/pull/340

In this release, we added support for rendering using Pygame, which improves the previously Matplotlib-based rendering procedure, this is a breaking change that removes `minigrid.utils.window.Window`. A bug in the SymbolicObsWrapper that results in the wrong observation has been fixed. An error in the documentation regarding the reward function has been corrected. The `ObstructedMaze` environments are now ensured to be solvable. The class `minigrid_env.MiniGridEnv.Actions` is removed since it is the same as `minigrid.core.actions.Actions`.

Bug Fixes and Documentation Updates
- For the `MiniGrid-DoorKey-6x6-v0` environment, a hidden variable determining the size was wrong at 5x5, this is updated to 6x6.
https://github.com/Farama-Foundation/Minigrid/pull/322
- Since the class `minigrid_env.MiniGridEnv.Actions` is the same as `minigrid.core.actions.Actions`, to make the codebase cleaner, we have deleted the class `minigrid_env.MiniGridEnv.Actions`. This is a breaking change. For any code that relies on `minigrid_env.MiniGridEnv.Actions`, you can simply replace it with `minigrid.core.actions.Actions`.
https://github.com/Farama-Foundation/Minigrid/pull/328
- In `SymbolicObsWrapper`, the grid that records the content of each tile is formatted as `[x, y, item]`, which corresponds to `[col, row, item]`, this causes a mismatch in the observation. This mismatch is now resolved.
https://github.com/Farama-Foundation/Minigrid/pull/331
- The documentation for the rewards has previously incorrectly stated that the reward is 1 when the environment is solved, while it is actually `1 - 0.9 * (step_count / max_steps)`. Additionally, in `GoToObjectEnv`, there was an error in detecting whether the agent is next to the target. These issues have now been resolved.
https://github.com/Farama-Foundation/Minigrid/pull/333
- Previously Minigrid relied on a Matplotlib-based rendering backend. We have added a Pygame-based rendering backend that is faster and more consistent with other Farama libraries. As a result, `minigrid.utils.window.Window` has been removed.
https://github.com/Farama-Foundation/Minigrid/pull/313
- In the `ObstructedMaze` environments, the blocking ball placed by `add_door` may cover the box placed on the map by the previous `add_door`, causing the agent to be unable to open certain doors and complete the task. We have updated several of the `ObstructedMaze` environments to be always solvable and are registered as `v1` versions of the environment.
https://github.com/Farama-Foundation/Minigrid/pull/334