Fix typos in python comments used to generate docs

Author: alex-mccarthy-unity

ml-agents-envs/mlagents_envs/registry/unity_env_registry.py

@@ -16,7 +16,7 @@ class UnityEnvRegistry(Mapping):
     The UnityEnvRegistry implements a Map, to access an entry of the Registry, use:
     ```python
     registry = UnityEnvRegistry()
-    entry = registry[<environment_identifyier>]
+    entry = registry[<environment_identifier>]
     ```
     An entry has the following properties :
      * `identifier` : Uniquely identifies this environment
@@ -27,7 +27,7 @@ class UnityEnvRegistry(Mapping):
     To launch a Unity environment from a registry entry, use the `make` method:
     ```python
     registry = UnityEnvRegistry()
-    env = registry[<environment_identifyier>].make()
+    env = registry[<environment_identifier>].make()
     ```
     """
 

ml-agents/mlagents/trainers/optimizer/torch_optimizer.py

@@ -148,8 +148,8 @@ def get_trajectory_value_estimates(
         """
         Get value estimates and memories for a trajectory, in batch form.
         :param batch: An AgentBuffer that consists of a trajectory.
-        :param next_obs: the next observation (after the trajectory). Used for boostrapping
-            if this is not a termiinal trajectory.
+        :param next_obs: the next observation (after the trajectory). Used for bootstrapping
+            if this is not a terminal trajectory.
         :param done: Set true if this is a terminal trajectory.
         :param agent_id: Agent ID of the agent that this trajectory belongs to.
         :returns: A Tuple of the Value Estimates as a Dict of [name, np.ndarray(trajectory_len)],

ml-agents/mlagents/trainers/poca/optimizer_torch.py

@@ -565,8 +565,8 @@ def get_trajectory_and_baseline_value_estimates(
         """
         Get value estimates, baseline estimates, and memories for a trajectory, in batch form.
         :param batch: An AgentBuffer that consists of a trajectory.
-        :param next_obs: the next observation (after the trajectory). Used for boostrapping
-            if this is not a termiinal trajectory.
+        :param next_obs: the next observation (after the trajectory). Used for bootstrapping
+            if this is not a terminal trajectory.
         :param next_groupmate_obs: the next observations from other members of the group.
         :param done: Set true if this is a terminal trajectory.
         :param agent_id: Agent ID of the agent that this trajectory belongs to.

ml-agents/mlagents/trainers/settings.py

@@ -517,7 +517,7 @@ def need_increment(
 class Lesson:
     """
     Gathers the data of one lesson for one environment parameter including its name,
-    the condition that must be fullfiled for the lesson to be completed and a sampler
+    the condition that must be fulfilled for the lesson to be completed and a sampler
     for the environment parameter. If the completion_criteria is None, then this is
     the last lesson in the curriculum.
     """