restructuring

alr_envs/examples/examples_dmc.py

@@ -69,7 +69,7 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
         "learn_goal": True,  # learn the goal position (recommended)
         "alpha_phase": 2,
         "bandwidth_factor": 2,
-        "policy_type": "motor",  # controller type, 'velocity', 'position', and 'motor' (torque control)
+        "policy_type": "motor",  # tracking_controller type, 'velocity', 'position', and 'motor' (torque control)
         "weights_scale": 1,  # scaling of MP weights
         "goal_scale": 1,  # scaling of learned goal position
         "policy_kwargs": {  # only required for torque control/PD-Controller
@@ -83,8 +83,8 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
         # "frame_skip": 1
     }
     env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs, **kwargs)
-    # OR for a deterministic ProMP (other mp_kwargs are required, see metaworld_examples):
-    # env = alr_envs.make_promp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_args)
+    # OR for a deterministic ProMP (other traj_gen_kwargs are required, see metaworld_examples):
+    # env = alr_envs.make_promp_env(base_env, wrappers=wrappers, seed=seed, traj_gen_kwargs=mp_args)
 
     # This renders the full MP trajectory
     # It is only required to call render() once in the beginning, which renders every consecutive trajectory.

alr_envs/examples/examples_metaworld.py

@@ -73,12 +73,12 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
         "width": 0.025,  # width of the basis functions
         "zero_start": True,  # start from current environment position if True
         "weights_scale": 1,  # scaling of MP weights
-        "policy_type": "metaworld",  # custom controller type for metaworld environments
+        "policy_type": "metaworld",  # custom tracking_controller type for metaworld environments
     }
 
     env = alr_envs.make_promp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs)
-    # OR for a DMP (other mp_kwargs are required, see dmc_examples):
-    # env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs, **kwargs)
+    # OR for a DMP (other traj_gen_kwargs are required, see dmc_examples):
+    # env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, traj_gen_kwargs=traj_gen_kwargs, **kwargs)
 
     # This renders the full MP trajectory
     # It is only required to call render() once in the beginning, which renders every consecutive trajectory.

alr_envs/examples/examples_motion_primitives.py

@@ -57,7 +57,7 @@ def example_custom_mp(env_name="alr_envs:HoleReacherDMP-v1", seed=1, iterations=
     Returns:
 
     """
-    # Changing the mp_kwargs is possible by providing them to gym.
+    # Changing the traj_gen_kwargs is possible by providing them to gym.
     # E.g. here by providing way to many basis functions
     mp_kwargs = {
         "num_dof": 5,
@@ -126,7 +126,7 @@ def example_fully_custom_mp(seed=1, iterations=1, render=True):
     }
     env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs)
     # OR for a deterministic ProMP:
-    # env = make_promp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs)
+    # env = make_promp_env(base_env, wrappers=wrappers, seed=seed, traj_gen_kwargs=traj_gen_kwargs)
 
     if render:
         env.render(mode="human")

alr_envs/examples/examples_open_ai.py

@@ -4,7 +4,7 @@ import alr_envs
 def example_mp(env_name, seed=1):
     """
     Example for running a motion primitive based version of a OpenAI-gym environment, which is already registered.
-    For more information on motion primitive specific stuff, look at the mp examples.
+    For more information on motion primitive specific stuff, look at the trajectory_generator examples.
     Args:
         env_name: ProMP env_id
         seed: seed

alr_envs/examples/pd_control_gain_tuning.py

@@ -8,7 +8,7 @@ from alr_envs.utils.make_env_helpers import make_promp_env
 
 def visualize(env):
     t = env.t
-    pos_features = env.mp.basis_generator.basis(t)
+    pos_features = env.trajectory_generator.basis_generator.basis(t)
     plt.plot(t, pos_features)
     plt.show()