mosaic-multigrid 0.2.0__tar.gz

mosaic_multigrid-0.2.0/LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   MiniGrid: Copyright 2020 Maxime Chevalier-Boisvert
+   Multi-agent Extension (MultiGrid): Copyright 2020 Arnaud Fickinger
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mosaic_multigrid-0.2.0/MANIFEST.in

@@ -0,0 +1,5 @@
+include README.md
+include LICENSE
+include NOTICE
+recursive-include mosaic_multigrid *.py
+recursive-include figures *.png

mosaic_multigrid-0.2.0/NOTICE

@@ -0,0 +1,15 @@
+mosaic_multigrid
+Copyright 2026 Abdulhamid Mousa
+
+This product is a derivative work based on gym-multigrid, which includes
+the following software:
+
+  Multi-Agent Gridworld Environment (MultiGrid)
+  Copyright 2020 Arnaud Fickinger
+  https://github.com/ArnaudFickinger/gym-multigrid
+
+  MiniGrid
+  Copyright 2020 Maxime Chevalier-Boisvert
+  https://github.com/maximecb/gym-minigrid
+
+Licensed under the Apache License, Version 2.0.

mosaic_multigrid-0.2.0/PKG-INFO

@@ -0,0 +1,299 @@
+Metadata-Version: 2.4
+Name: mosaic_multigrid
+Version: 0.2.0
+Summary: Research-grade multi-agent gridworld environments for reproducible RL experiments
+Home-page: https://github.com/Abdulhamid97Mousa/mosaic_multigrid
+Author: Abdulhamid Mousa
+Author-email: Abdulhamid Mousa <abdulhamid97mousa@gmail.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/Abdulhamid97Mousa/mosaic_multigrid
+Project-URL: Repository, https://github.com/Abdulhamid97Mousa/mosaic_multigrid
+Keywords: reinforcement-learning,multi-agent,gymnasium,gridworld,soccer,competitive
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: aenum>=1.3.0
+Requires-Dist: numba>=0.53.0
+Requires-Dist: numpy>=1.18.0
+Requires-Dist: gymnasium>=0.26
+Requires-Dist: pygame>=2.2.0
+Provides-Extra: rllib
+Requires-Dist: ray[rllib]>=2.0; extra == "rllib"
+Provides-Extra: pettingzoo
+Requires-Dist: pettingzoo>=1.22; extra == "pettingzoo"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-timeout>=2.0; extra == "dev"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# mosaic_multigrid
+
+**Research-grade multi-agent gridworld environments for reproducible RL experiments.**
+
+A maintained fork of [gym-multigrid](https://github.com/ArnaudFickinger/gym-multigrid) by Arnaud Fickinger (2020), modernized to the Gymnasium API with Numba JIT-accelerated observations, reproducible seeding, and multi-agent framework adapters.
+
+This fork is developed as part of the [MOSAIC](https://github.com/Abdulhamid97Mousa/MOSAIC) project (Multi-Agent Orchestration System).
+
+## What Changed from Upstream
+
+| Aspect | Upstream (Fickinger 2020) | This Fork |
+|--------|--------------------------|-----------|
+| API | Old Gym 4-tuple, list-based | Gymnasium 5-tuple, dict-keyed per agent |
+| Actions | 8 (still=0..done=7) | 7 (left=0..done=6), no "still" |
+| Observations | `(view, view, 6)` list | `(view, view, 3)` dict with `image`, `direction`, `mission` |
+| `reset()` | `List[obs]` | `(Dict[int, obs], Dict[int, info])` |
+| `step()` | `(List[obs], ndarray, bool, dict)` | `(Dict, Dict, Dict, Dict, Dict)` |
+| Render | `render(mode='human')` param | `render_mode` constructor param |
+| Seeding | `env.seed(42)` + broken global RNG | `reset(seed=42)` + `self.np_random` |
+| Window | matplotlib | pygame |
+| Performance | Pure Python loops | Numba JIT on observation generation |
+| Structure | 1 monolithic 1442-line file | ~20 focused modules |
+| Dependencies | `gym>=0.9.6, numpy` | `gymnasium>=0.26, numpy, numba, pygame, aenum` |
+
+### Bugs Fixed
+
+1. **Reproducibility bug** (critical): `step()` used `np.random.permutation()` (global RNG) for action ordering. Now uses `self.np_random.random(size=N).argsort()` to respect environment seeding.
+2. **No `render_mode`**: Constructor now accepts `render_mode='rgb_array'` or `render_mode='human'`, following Gymnasium convention.
+3. **Legacy 4-tuple**: `step()` returns Gymnasium 5-tuple `(obs, rewards, terminated, truncated, info)` with per-agent dicts.
+
+## Included Environments
+
+### SoccerGame
+
+<p align="center">
+  <img src="figures/soccer.png" width="200">
+  <img src="figures/soccer_2.png" width="200">
+  <img src="figures/soccer_4.png" width="200">
+</p>
+
+Team-based competitive environment. Agents score by dropping the ball at the opposing team's goal. Supports ball passing, stealing, and zero-sum team rewards.
+
+**Default variant:** `SoccerGame4HEnv10x15N2` -- 4 agents (2v2), 15x10 grid, 1 ball.
+
+### CollectGame
+
+<p align="center">
+  <img src="figures/collect.png" width="200">
+  <img src="figures/collect_2.png" width="200">
+</p>
+
+Cooperative/competitive collection. Agents earn rewards for picking up same-color balls and penalties for different-color balls.
+
+**Default variant:** `CollectGame4HEnv10x10N2` -- 4 agents, 10x10 grid, 2 ball colors.
+
+## Installation
+
+### From PyPI (recommended)
+
+```bash
+pip install mosaic-multigrid
+
+# With optional framework adapters
+pip install mosaic-multigrid[rllib]       # Ray RLlib support
+pip install mosaic-multigrid[pettingzoo]  # PettingZoo support
+pip install mosaic-multigrid[dev]         # pytest
+```
+
+### From source
+
+```bash
+git clone https://github.com/Abdulhamid97Mousa/mosaic_multigrid.git
+cd mosaic_multigrid
+pip install -e .
+```
+
+## Quick Start
+
+```python
+from mosaic_multigrid.envs import SoccerGame4HEnv10x15N2
+
+env = SoccerGame4HEnv10x15N2(render_mode='rgb_array')
+obs, info = env.reset(seed=42)
+
+# obs is a dict keyed by agent index: {0: {...}, 1: {...}, 2: {...}, 3: {...}}
+# Each agent's obs has 'image', 'direction', 'mission' keys
+
+actions = {i: env.action_space[i].sample() for i in range(env.num_agents)}
+obs, rewards, terminated, truncated, info = env.step(actions)
+
+# Render RGB frame
+frame = env.render()  # Returns numpy array (H, W, 3)
+env.close()
+```
+
+### Reproducibility
+
+```python
+# Same seed → identical trajectories (reproducibility bug is fixed)
+for trial in range(2):
+    env = SoccerGame4HEnv10x15N2(render_mode='rgb_array')
+    obs, _ = env.reset(seed=42)
+    for step in range(100):
+        actions = {i: 2 for i in range(4)}  # all forward
+        obs, *_ = env.step(actions)
+    # obs will be identical across trials
+```
+
+## Architecture
+
+```
+gym_multigrid/
+├── base.py                  # MultiGridEnv (Gymnasium-compliant base)
+├── core/
+│   ├── constants.py         # Type, Color, State, Direction enums
+│   ├── actions.py           # Action enum (7 actions, no "still")
+│   ├── world_object.py      # WorldObj numpy-subclass + all object types
+│   ├── agent.py             # Agent + AgentState (vectorized, team_index)
+│   ├── grid.py              # Grid (numpy state + world_objects cache)
+│   └── mission.py           # Mission + MissionSpace
+├── utils/
+│   ├── enum.py              # IndexedEnum (aenum-based, dynamically extensible)
+│   ├── rendering.py         # Tile rendering (fill_coords, downsample, etc.)
+│   ├── random.py            # RandomMixin (seeded RNG utilities)
+│   ├── obs.py               # Numba JIT observation generation (hot path)
+│   └── misc.py              # front_pos, PropertyAlias
+├── envs/
+│   ├── soccer_game.py       # SoccerGameEnv + variants
+│   └── collect_game.py      # CollectGameEnv + variants
+├── wrappers.py              # FullyObs, ImgObs, OneHotObs, SingleAgent
+├── pettingzoo/              # PettingZoo ParallelEnv adapter
+└── rllib/                   # Ray RLlib MultiAgentEnv adapter
+```
+
+### Core Design Decisions
+
+**Agent-not-in-grid**: Agents are NOT stored on the grid (following multigrid-ini). Agent positions are tracked via `AgentState.pos`. The observation generator inserts agents into the observation grid dynamically. This avoids grid corruption when agents overlap.
+
+**numpy subclass pattern**: `WorldObj(np.ndarray)` and `AgentState(np.ndarray)` — domain objects ARE their numerical encoding. No serialization overhead.
+
+**team_index separation**: `agent.index` (unique identity) vs `agent.team_index` (team membership). The original code conflated these — your agent index WAS your team.
+
+**Numba JIT**: All observation generation functions use `@nb.njit(cache=True)`. Enum values are extracted to plain `int` constants at module level because Numba cannot access Python enum attributes.
+
+## Action Space
+
+### Action Enum Comparison
+
+| Action | Upstream (Fickinger 2020) | mosaic_multigrid (this fork) | multigrid-ini (Oguntola 2023) |
+|--------|---:|---:|---:|
+| still | **0** | -- | -- |
+| left | 1 | **0** | **0** |
+| right | 2 | **1** | **1** |
+| forward | 3 | **2** | **2** |
+| pickup | 4 | **3** | **3** |
+| drop | 5 | **4** | **4** |
+| toggle | 6 | **5** | **5** |
+| done | 7 | **6** | **6** |
+| **Total** | **8** | **7** | **7** |
+
+The `still` action (do nothing) was removed. Agents that need to skip a turn send `Action.done` instead. This aligns with multigrid-ini and shrinks the action space from 8 to 7.
+
+> **Migration note:** All action indices shifted down by 1 compared to the upstream code. Any pre-trained policy or hardcoded action mapping from the old environment will need updating.
+
+## Observation Space
+
+Each agent receives a partial observation dict:
+
+```python
+{
+    'image': np.ndarray,     # (view_size, view_size, 3) — [Type, Color, State] per cell
+    'direction': int,        # Agent facing direction (0=right, 1=down, 2=left, 3=up)
+    'mission': str,          # Mission string
+}
+```
+
+The default `view_size=7` gives each agent a 7x7 partial view. Each cell encodes 3 values (Type index, Color index, State index), down from 6 in the original.
+
+## Wrappers
+
+| Wrapper | Description |
+|---------|-------------|
+| `FullyObsWrapper` | Full grid observation instead of partial agent view |
+| `ImgObsWrapper` | Returns only the image array (drops direction/mission) |
+| `OneHotObsWrapper` | One-hot encodes the observation image (Numba JIT) |
+| `SingleAgentWrapper` | Unwraps multi-agent dict for single-agent use |
+
+## Framework Adapters
+
+### PettingZoo
+
+```python
+from gym_multigrid.pettingzoo import to_pettingzoo_env
+
+env = to_pettingzoo_env('MosaicMultiGrid-Soccer-v0', render_mode='rgb_array')
+# Returns a PettingZoo ParallelEnv
+```
+
+### Ray RLlib
+
+```python
+from gym_multigrid.rllib import to_rllib_env
+
+env_cls = to_rllib_env('MosaicMultiGrid-Soccer-v0')
+# Returns an RLlib MultiAgentEnv class (adds __all__ keys to terminated/truncated)
+```
+
+## Requirements
+
+- Python >= 3.9
+- gymnasium >= 0.26
+- numpy >= 1.18
+- numba >= 0.53
+- pygame >= 2.2
+- aenum >= 1.3
+
+**Optional:**
+- `ray[rllib] >= 2.0` (for RLlib adapter)
+- `pettingzoo >= 1.22` (for PettingZoo adapter)
+
+## Tests
+
+```bash
+pip install -e ".[dev]"
+pytest tests/ -v
+```
+
+94 tests covering: Action enum, Type/Color/State/Direction enums, WorldObj encode/decode, Grid operations, AgentState vectorized ops, Agent team_index, Mission/MissionSpace, MultiGridEnv reset/step/render, pickup/drop mechanics, Numba JIT observations, rendering dimensions, and reproducibility.
+
+## Citation
+
+If you use this environment, please cite both the original work and this fork:
+
+```bibtex
+@misc{gym_multigrid,
+  author = {Fickinger, Arnaud},
+  title = {Multi-Agent Gridworld Environment for OpenAI Gym},
+  year = {2020},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/ArnaudFickinger/gym-multigrid}},
+}
+
+@misc{mosaic_multigrid,
+  author = {Mousa, Abdulhamid},
+  title = {mosaic\_multigrid: Research-Grade Multi-Agent Gridworld Environments},
+  year = {2026},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/Abdulhamid97Mousa/mosaic_multigrid}},
+}
+```
+
+## License
+
+Apache License 2.0 -- see [LICENSE](LICENSE) for details.
+
+**Original work:** MiniGrid (Copyright 2020 Maxime Chevalier-Boisvert), MultiGrid extension (Copyright 2020 Arnaud Fickinger).
+**This fork:** Copyright 2026 Abdulhamid Mousa.