Merge pull request #42 from Farama-Foundation/feature/cleanup_experim…

…ental_script

Experimental launch script

README.md

@@ -65,6 +65,21 @@ For details on multi-objective multi-agent RL definitions, see [Multi-Objective
 You can also check more examples in this colab notebook! [![MOMAland Demo in Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Farama-Foundation/momaland/blob/doc/notebook/momaland_demo.ipynb)
 <!-- end snippet-usage -->
 
+## Learning Algorithms
+<!-- start learning-algorithms -->
+We provide a set of learning algorithms that are compatible with the MOMAland environments. The learning algorithms are implemented in the [learning/](https://github.com/Farama-Foundation/momaland/tree/main/momaland/learning) directory. To keep everything as self-contained as possible, each algorithm is implemented as a single-file (close to [cleanRL's philosophy](https://github.com/vwxyzjn/cleanrl/tree/master)).
+
+Nevertheless, we reuse tools provided by other libraries, like multi-objective evaluations and performance indicators from [MORL-Baselines](https://github.com/LucasAlegre/morl-baselines).
+
+Here is a list of algorithms that are currently implemented:
+
+| **Name**                                                                                                                                                                                                                                                            | Single/Multi-policy | Reward | Utility       | Observation space | Action space | Paper |
+|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------|--------|---------------|-------------------|--------------|-------|
+| MOMAPPO (OLS) [continuous](https://github.com/Farama-Foundation/momaland/blob/main/momaland/learning/continuous/cooperative_momappo.py),<br/> [discrete](https://github.com/Farama-Foundation/momaland/blob/main/momaland/learning/discrete/cooperative_momappo.py) | Multi               | Team   | Team / Linear | Any               | Any          |       |
+
+
+<!-- end learning-algorithms -->
+
 ## Environment Versioning
 MOMAland keeps strict versioning for reproducibility reasons. All environments end in a suffix like "_v0".  When changes are made to environments that might impact learning results, the number is increased by one to prevent potential confusion.
 

docs/index.md

@@ -32,7 +32,7 @@ environments/all-envs
 :caption: Tutorials
 
 tutorials/custom_env
-tutorials/training
+tutorials/learning_algorithms
 ```
 
 ```{toctree}

docs/tutorials/learning_algorithms.md

@@ -0,0 +1,9 @@
+---
+title: Learning algorithms
+---
+
+# Learning algorithms
+```{include} ../../README.md
+:start-after: <!-- start learning-algorithms -->
+:end-before: <!-- end learning-algorithms -->
+```

momaland/__init__.py

@@ -1,6 +1,7 @@
 """Export everything in the repo for import from other libraries."""
 
 import momaland.envs
+import momaland.learning
 import momaland.utils
 
 

momaland/envs/crazyrl/crazyRL_base.py

@@ -7,45 +7,8 @@
 import numpy.typing as npt
 import pygame
 from gymnasium import spaces
-from OpenGL.GL import (
-    GL_AMBIENT,
-    GL_AMBIENT_AND_DIFFUSE,
-    GL_BLEND,
-    GL_COLOR_BUFFER_BIT,
-    GL_COLOR_MATERIAL,
-    GL_DEPTH_BUFFER_BIT,
-    GL_DEPTH_TEST,
-    GL_DIFFUSE,
-    GL_FRONT_AND_BACK,
-    GL_LIGHT0,
-    GL_LIGHTING,
-    GL_MODELVIEW,
-    GL_MODELVIEW_MATRIX,
-    GL_ONE_MINUS_SRC_ALPHA,
-    GL_POSITION,
-    GL_PROJECTION,
-    GL_SMOOTH,
-    GL_SRC_ALPHA,
-    glBlendFunc,
-    glClear,
-    glColor4f,
-    glColorMaterial,
-    glEnable,
-    glGetFloatv,
-    glLight,
-    glLightfv,
-    glLineWidth,
-    glLoadIdentity,
-    glMatrixMode,
-    glMultMatrixf,
-    glPopMatrix,
-    glPushMatrix,
-    glShadeModel,
-)
-from OpenGL.raw.GLU import gluLookAt, gluPerspective
 from pygame import DOUBLEBUF, OPENGL
 
-from momaland.envs.crazyrl.gl_utils import axes, field, point, target_point
 from momaland.utils.env import MOParallelEnv
 
 
@@ -313,6 +276,44 @@ def step(self, actions):
     @override
     def render(self):
         """Renders the current frame of the environment. Only works in human rendering mode."""
+        from OpenGL.GL import (
+            GL_AMBIENT,
+            GL_AMBIENT_AND_DIFFUSE,
+            GL_BLEND,
+            GL_COLOR_BUFFER_BIT,
+            GL_COLOR_MATERIAL,
+            GL_DEPTH_BUFFER_BIT,
+            GL_DEPTH_TEST,
+            GL_DIFFUSE,
+            GL_FRONT_AND_BACK,
+            GL_LIGHT0,
+            GL_LIGHTING,
+            GL_MODELVIEW,
+            GL_MODELVIEW_MATRIX,
+            GL_ONE_MINUS_SRC_ALPHA,
+            GL_POSITION,
+            GL_PROJECTION,
+            GL_SMOOTH,
+            GL_SRC_ALPHA,
+            glBlendFunc,
+            glClear,
+            glColor4f,
+            glColorMaterial,
+            glEnable,
+            glGetFloatv,
+            glLight,
+            glLightfv,
+            glLineWidth,
+            glLoadIdentity,
+            glMatrixMode,
+            glMultMatrixf,
+            glPopMatrix,
+            glPushMatrix,
+            glShadeModel,
+        )
+        from OpenGL.raw.GLU import gluLookAt, gluPerspective
+
+        from momaland.envs.crazyrl.gl_utils import axes, field, point, target_point
 
         def init_window():
             """Initializes the PyGame window."""

momaland/learning/__init__.py

@@ -0,0 +1 @@
+"""Learning module for momaland."""

momaland/learning/cooperative_momappo/__init__.py

@@ -0,0 +1 @@
+"""Cooperative MOMAPPO."""