Merge pull request #59 from beyretb/dev-v1.0.5

Dev v1.0.5

README.md

@@ -167,11 +167,12 @@ features with the agent's frames in order to have frames in line with the config
 
 ## Version History
 
-- v1.0.4
+- v1.0.5
     - Adds customisable resolution during evaluation
     - Update `animalai-train` to tf 1.14 to fix `gin` broken dependency
     - Release source code for the environment (no support to be provided on this for now)
-
+    - Fixes some legacy dependencies and typos in both libraries
+    
 - v1.0.3
     - Adds inference mode to Gym environment
     - Adds seed to Gym Environment

animalai/animalai/envs/gym/environment.py

@@ -56,7 +56,7 @@ class AnimalAIEnv(gym.Env):
                                      arenas_configurations=arenas_configurations,
                                      inference=inference,
                                      resolution=resolution)
-        # self.name = self._env.academy_name
+        self.name = 'aaio'
         self.vector_obs = None
         self.inference = inference
         self.resolution = resolution

animalai/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name='animalai',
-    version='1.0.3',
+    version='1.0.5',
     description='Animal AI competition interface',
     url='https://github.com/beyretb/AnimalAI-Olympics',
     author='Benjamin Beyret',

examples/animalai_train/animalai_train/trainers/curriculum.py

@@ -10,12 +10,10 @@ logger = logging.getLogger('mlagents.trainers')
 
 
 class Curriculum(object):
-    def __init__(self, location, default_reset_parameters):
+    def __init__(self, location):
         """
         Initializes a Curriculum object.
         :param location: Path to JSON defining curriculum.
-        :param default_reset_parameters: Set of reset parameters for
-               environment.
         """
         self.max_lesson_num = 0
         self.measure = None
@@ -47,10 +45,10 @@ class Curriculum(object):
 
         parameters = self.data['parameters']
         for key in parameters:
-            if key not in default_reset_parameters:
-                raise CurriculumError(
-                    'The parameter {0} in Curriculum {1} is not present in '
-                    'the Environment'.format(key, location))
+            # if key not in default_reset_parameters:
+            #     raise CurriculumError(
+            #         'The parameter {0} in Curriculum {1} is not present in '
+            #         'the Environment'.format(key, location))
             if len(parameters[key]) != self.max_lesson_num + 1:
                 raise CurriculumError(
                     'The parameter {0} in Curriculum {1} must have {2} values '

examples/animalai_train/animalai_train/trainers/learn.py

@@ -92,7 +92,7 @@ def try_create_meta_curriculum(curriculum_folder: Optional[str], env: UnityEnvir
     if curriculum_folder is None:
         return None
     else:
-        meta_curriculum = MetaCurriculum(curriculum_folder, env._resetParameters)
+        meta_curriculum = MetaCurriculum(curriculum_folder)
         if meta_curriculum:
             for brain_name in meta_curriculum.brains_to_curriculums.keys():
                 if brain_name not in env.external_brain_names:
@@ -167,8 +167,7 @@ def init_environment(env_path, docker_target_name, no_graphics, worker_id, fast_
         file_name=env_path,
         worker_id=worker_id,
         seed=seed,
-        docker_training=docker_training,
-        no_graphics=no_graphics
+        docker_training=docker_training
     )
 
 

examples/animalai_train/animalai_train/trainers/meta_curriculum.py

@@ -14,7 +14,7 @@ class MetaCurriculum(object):
     particular brain in the environment.
     """
 
-    def __init__(self, curriculum_folder, default_reset_parameters):
+    def __init__(self, curriculum_folder):
         """Initializes a MetaCurriculum object.
 
         Args:
@@ -22,8 +22,6 @@ class MetaCurriculum(object):
                 folder which holds the curriculums for this environment.
                 The folder should contain JSON files whose names are the
                 brains that the curriculums belong to.
-            default_reset_parameters (dict): The default reset parameters
-                of the environment.
         """
         used_reset_parameters = set()
         self._brains_to_curriculums = {}
@@ -33,8 +31,7 @@ class MetaCurriculum(object):
                 brain_name = curriculum_filename.split('.')[0]
                 curriculum_filepath = \
                     os.path.join(curriculum_folder, curriculum_filename)
-                curriculum = Curriculum(curriculum_filepath,
-                                        default_reset_parameters)
+                curriculum = Curriculum(curriculum_filepath)
 
                 # Check if any two curriculums use the same reset params.
                 if any([(parameter in curriculum.get_config().keys())

examples/animalai_train/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name='animalai_train',
-    version='1.0.4',
+    version='1.0.5',
     description='Animal AI competition training library',
     url='https://github.com/beyretb/AnimalAI-Olympics',
     author='Benjamin Beyret',
@@ -20,7 +20,7 @@ setup(
     zip_safe=False,
 
     install_requires=[
-        'animalai>=1.0.3',
+        'animalai>=1.0.5',
         'dopamine-rl',
         'tensorflow==1.14',
         'matplotlib',
@@ -31,6 +31,7 @@ setup(
         'pyyaml>=5.1',
         'atari-py',
         'jsonpickle>=1.2',
+        'docopt',
         'pypiwin32==223;platform_system=="Windows"'],
     python_requires=">=3.5,<3.8",
 )

examples/submission/agent.py

@@ -46,9 +46,11 @@ class Agent(object):
 
     def step(self, obs, reward, done, info):
         """
-        A single step the agent should take based on the current
-        :param brain_info:  a single BrainInfo containing the observations and reward for a single step for one agent
-        :return:            a list of actions to execute (of size 2)
+        :param obs: agent's observation of the current environment
+        :param reward: amount of reward returned after previous action
+        :param done: whether the episode has ended.
+        :param info: contains auxiliary diagnostic information, including BrainInfo.
+        :return: the action to take, a list or size 2
         """
 
         brain_info = info['brain_info']