Full Observability, New Interface

.gitignore

@@ -1 +1,152 @@
+# Byte-compiled / optimized / DLL files
 __pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

gym_multigrid/envs/__init__.py

@@ -1,2 +1,2 @@
-from gym_multigrid.envs.collect_game import CollectGame4HEnv10x10N2
-from gym_multigrid.envs.soccer_game import SoccerGame4HEnv10x15N2
+from gym_multigrid.envs.collect_game import CollectGameEnv
+from gym_multigrid.envs.soccer_game import SoccerGameEnv

gym_multigrid/envs/collect_game.py

@@ -15,6 +15,7 @@ def __init__(
         balls_index=[],
         balls_reward=[],
         zero_sum = False,
+        partial_obs=True,
         view_size=7
 
     ):
@@ -37,6 +38,7 @@ def __init__(
             # Set this to True for maximum speed
             see_through_walls=False,
             agents=agents,
+            partial_obs=partial_obs,
             agent_view_size=view_size
         )
 
@@ -84,15 +86,4 @@ def _handle_drop(self, i, rewards, fwd_pos, fwd_cell):
 
     def step(self, actions):
         obs, rewards, done, info = MultiGridEnv.step(self, actions)
-        return obs, rewards, done, info
-
-
-class CollectGame4HEnv10x10N2(CollectGameEnv):
-    def __init__(self):
-        super().__init__(size=10,
-        num_balls=[5],
-        agents_index = [1,2,3],
-        balls_index=[0],
-        balls_reward=[1],
-        zero_sum=True)
-
+        return obs, rewards, done, info

gym_multigrid/envs/soccer_game.py

@@ -9,6 +9,7 @@ def __init__(
         self,
         size=10,
         view_size=3,
+        partial_obs=True,
         width=None,
         height=None,
         goal_pst = [],
@@ -39,6 +40,7 @@ def __init__(
             # Set this to True for maximum speed
             see_through_walls=False,
             agents=agents,
+            partial_obs=partial_obs,
             agent_view_size=view_size
         )
 
@@ -102,17 +104,4 @@ def _handle_drop(self, i, rewards, fwd_pos, fwd_cell):
 
     def step(self, actions):
         obs, rewards, done, info = MultiGridEnv.step(self, actions)
-        return obs, rewards, done, info
-
-
-class SoccerGame4HEnv10x15N2(SoccerGameEnv):
-    def __init__(self):
-        super().__init__(size=None,
-        height=10,
-        width=15,
-        goal_pst = [[1,5], [13,5]],
-        goal_index = [1,2],
-        num_balls=[1],
-        agents_index = [1,1,2,2],
-        balls_index=[0],
-        zero_sum=True)
+        return obs, rewards, done, info

gym_multigrid/multigrid.py

@@ -974,7 +974,7 @@ def reset(self):
         if self.partial_obs:
             obs = self.gen_obs()
         else:
-            obs = [self.grid.encode_for_agents(self.agents[i].pos) for i in range(len(self.agents))]
+            obs = [self.grid.encode_for_agents(world=self.world, agent_pos=self.agents[i].pos) for i in range(len(self.agents))]
         obs=[self.objects.normalize_obs*ob for ob in obs]
         return obs
 
@@ -1315,7 +1315,7 @@ def step(self, actions):
         if self.partial_obs:
             obs = self.gen_obs()
         else:
-            obs = [self.grid.encode_for_agents(self.agents[i].pos) for i in range(len(actions))]
+            obs = [self.grid.encode_for_agents(world=self.world, agent_pos=self.agents[i].pos) for i in range(len(actions))]
 
         obs=[self.objects.normalize_obs*ob for ob in obs]
 

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup
 
 setup(name='gym_multigrid',
-      version='0.0.1',
+      version='0.0.2',
         packages=['gym_multigrid', 'gym_multigrid.envs'],
         install_requires=[
         'gym>=0.9.6',

test_env.py

@@ -13,14 +13,18 @@ def main():
     if args.env == 'soccer':
         register(
             id='multigrid-soccer-v0',
-            entry_point='gym_multigrid.envs:SoccerGame4HEnv10x15N2',
+            entry_point='gym_multigrid.envs:SoccerGameEnv',
+            kwargs={'size': None, 'height': 10, 'width': 15, 'goal_pst': [[1,5], [13,5]], 'goal_index': [1,2], 'num_balls': [1], 
+            'agents_index': [1,1,2,2], 'balls_index': [0], 'zero_sum': True}
         )
         env = gym.make('multigrid-soccer-v0')
 
     else:
         register(
             id='multigrid-collect-v0',
-            entry_point='gym_multigrid.envs:CollectGame4HEnv10x10N2',
+            entry_point='gym_multigrid.envs:CollectGameEnv',
+            kwargs={'size': 10,'num_balls': [5], 'agents_index': [1,2,3], 'balls_index': [0], 'balls_reward': [1], 'zero_sum': True, 'partial_obs': False},
+
         )
         env = gym.make('multigrid-collect-v0')
 
@@ -29,7 +33,7 @@ def main():
     nb_agents = len(env.agents)
 
     while True:
-        env.render(mode='human', highlight=True)
+        env.render(mode='human', highlight=True if env.partial_obs else False)
         time.sleep(0.1)
 
         ac = [env.action_space.sample() for _ in range(nb_agents)]