Testing gym with basic environment (#3725)

* Trying to build a specific environment

* forgot to replace one testPlayer

* reverting 3DBall to default

* removed the multi-agent test and replaced it with a single agent test

* forgot to add this file...

.yamato/gym-interface-test.yml

   commands:
     - pip install pyyaml
     - python -u -m ml-agents.tests.yamato.setup_venv
-    - ./venv/bin/python ml-agents/tests/yamato/scripts/run_gym.py
+    - ./venv/bin/python ml-agents/tests/yamato/scripts/run_gym.py --env=Project/testPlayer-Basic
   dependencies:
     - .yamato/standalone-build-test.yml#test_mac_standalone_{{ editor.version }}
   triggers:

.yamato/python-ll-api-test.yml

     - python -u -m ml-agents.tests.yamato.setup_venv
     - ./venv/bin/python ml-agents/tests/yamato/scripts/run_llapi.py
   dependencies:
-    - .yamato/standalone-build-test.yml#test_mac_standalone_{{ editor.version }}
+    - .yamato/standalone-build-test.yml#test_mac_standalone_{{ editor.version }} --env=Project/testPlayer
   triggers:
     cancel_old_ci: true
     changes:

.yamato/standalone-build-test.yml

   commands:
     - pip install pyyaml
     - python -u -m ml-agents.tests.yamato.standalone_build_tests
+    - python -u -m ml-agents.tests.yamato.standalone_build_tests --scene=Assets/ML-Agents/Examples/Basic/Scenes/Basic.unity
   triggers:
     cancel_old_ci: true
     changes:

ml-agents/tests/yamato/scripts/run_gym.py

 import argparse
-import numpy as np
 
 from gym_unity.envs import UnityEnv
 
     Run the gym test using the specified environment
     :param env_name: Name of the Unity environment binary to launch
     """
-    multi_env = UnityEnv(
-        env_name, worker_id=1, use_visual=False, multiagent=True, no_graphics=True
-    )
+    env = UnityEnv(env_name, worker_id=1, use_visual=False, no_graphics=True)
-        print(str(multi_env))
+        print(str(env))
-        initial_observations = multi_env.reset()
+        initial_observations = env.reset()
-        if len(multi_env.observation_space.shape) == 1:
+        if len(env.observation_space.shape) == 1:
-            print("Agent observations look like: \n{}".format(initial_observations[0]))
+            print("Agent observations look like: \n{}".format(initial_observations))
-            multi_env.reset()
+            env.reset()
-                actions = [
-                    multi_env.action_space.sample()
-                    for agent in range(multi_env.number_agents)
-                ]
-                observations, rewards, dones, info = multi_env.step(actions)
-                episode_rewards += np.mean(rewards)
-                done = dones[0]
+                actions = env.action_space.sample()
+                obs, reward, done, _ = env.step(actions)
+                episode_rewards += reward
-        multi_env.close()
+        env.close()
 
 
 if __name__ == "__main__":

ml-agents/tests/yamato/standalone_build_tests.py

 import sys
+import argparse
-def main():
+def main(scene_path):
-    returncode = run_standalone_build(base_path, verbose=True)
+    executable_name = None
+    if scene_path is not None:
+        executable_name = scene_path.strip(".unity")
+        executable_name = executable_name.split("/")[-1]
+        executable_name = "testPlayer-" + executable_name
+
+    returncode = run_standalone_build(
+        base_path, verbose=True, output_path=executable_name, scene_path=scene_path
+    )
 
     if returncode == 0:
         print("Test run SUCCEEDED!")
 
 
 if __name__ == "__main__":
-    main()
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--scene", default=None)
+    args = parser.parse_args()
+    main(args.scene)

ml-agents/tests/yamato/yamato_utils.py

 
 
 def run_standalone_build(
-    base_path: str, verbose: bool = False, output_path: str = None
+    base_path: str,
+    verbose: bool = False,
+    output_path: str = None,
+    scene_path: str = None,
 ) -> int:
     """
     Run BuildStandalonePlayerOSX test to produce a player. The location defaults to Project/testPlayer.
         test_args += ["-logfile", "-"]
     if output_path is not None:
         test_args += ["--mlagents-build-output-path", output_path]
+    if scene_path is not None:
+        test_args += ["--mlagents-build-scene-path", scene_path]
     print(f"{' '.join(test_args)} ...")
 
     timeout = 30 * 60  # 30 minutes, just in case