advances on gymnasium compatibility: environment header is now execut…

…ed during environment creation

deprl/custom_distributed.py

@@ -264,6 +264,8 @@ def distribute(
         env=environment, parallel=parallel, sequential=sequential
     )
 
+    if "header" in tonic_conf:
+        exec(tonic_conf["header"])
     dummy_environment = build_env_from_dict(build_dict)
     max_episode_steps = dummy_environment._max_episode_steps
     del dummy_environment

deprl/vendor/tonic/environments/builders.py

@@ -5,34 +5,42 @@
 
 import gym.wrappers
 import numpy as np
+from myosuite.utils import gym
 
 from deprl.vendor.tonic import environments
 from deprl.vendor.tonic.utils import logger
 
 
 def gym_environment(*args, **kwargs):
     """Returns a wrapped Gym environment."""
+    if "header" in kwargs:
+        kwargs.pop("header")
 
     def _builder(*args, **kwargs):
         return gym.make(*args, **kwargs)
 
-    return build_environment(_builder, *args, **kwargs)
+    return build_environment(_builder, *args, **kwargs, header=None)
 
 
 def bullet_environment(*args, **kwargs):
     """Returns a wrapped PyBullet environment."""
+    if "header" in kwargs:
+        kwargs.pop("header")
 
     def _builder(*args, **kwargs):
         import pybullet_envs  # noqa
 
         return gym.make(*args, **kwargs)
 
-    return build_environment(_builder, *args, **kwargs)
+    return build_environment(_builder, *args, **kwargs, header=None)
 
 
 def control_suite_environment(*args, **kwargs):
     """Returns a wrapped Control Suite environment."""
 
+    if "header" in kwargs:
+        kwargs.pop("header")
+
     def _builder(name, *args, **kwargs):
         domain, task = name.split("-")
         environment = ControlSuiteEnvironment(
@@ -44,7 +52,7 @@ def _builder(name, *args, **kwargs):
         )
         return gym.wrappers.TimeLimit(environment, time_limit)
 
-    return build_environment(_builder, *args, **kwargs)
+    return build_environment(_builder, *args, **kwargs, header=None)
 
 
 def build_environment(
@@ -54,6 +62,7 @@ def build_environment(
     time_feature=False,
     max_episode_steps="default",
     scaled_actions=True,
+    header=None,
     *args,
     **kwargs,
 ):
@@ -62,6 +71,8 @@ def build_environment(
     time_feature=True, see https://arxiv.org/pdf/1712.00378.pdf for more
     details.
     """
+    if header is not None:
+        exec(header)
 
     # Build the environment.
     environment = builder(name, *args, **kwargs)

experiments/myosuite_training_files/myoLegWalk.yaml

@@ -28,12 +28,12 @@ tonic:
   environment: deprl.environments.Gym('myoLegWalk-v0', scaled_actions=False, reset_type='random')
   environment_name: deprl_baseline
   full_save: 1
-  header: import deprl, gym, myosuite
+  header: import deprl, myosuite; from myosuite.utils import gym
   name: myoLeg
-  parallel: 20
+  parallel: 1
   resume: 1
   seed: 0
-  sequential: 10
+  sequential: 1
   test_environment: null
   trainer: deprl.custom_trainer.Trainer(steps=int(1e8), epoch_steps=int(2e5), save_steps=int(1e6))
 working_dir: ./baselines_DEPRL