update document

docs/Learning-Environment-Create-New.md

@@ -76,7 +76,7 @@ to seek, and a Sphere to represent the Agent itself.
 1. Right click in Hierarchy window, select 3D Object > Cube.
 1. Name the GameObject "Target"
 1. Select the Target Cube to view its properties in the Inspector window.
-1. Set Transform to Position = `3, 0.5, 3)`, Rotation = `(0, 0, 0)`, Scale =
+1. Set Transform to Position = `(3, 0.5, 3)`, Rotation = `(0, 0, 0)`, Scale =
    `(1, 1, 1)`.
 
 <p align="left">
@@ -136,7 +136,7 @@ Then, edit the new `RollerAgent` script:
 1. In the Unity Project window, double-click the `RollerAgent` script to open it
    in your code editor.
 1. In the editor, add the `using Unity.MLAgents;` and
-   `using Unity.MLAgents.Sensors` statements and then change the base class from
+   `using Unity.MLAgents.Sensors;` statements and then change the base class from
    `MonoBehaviour` to `Agent`.
 1. Delete the `Update()` method, but we will use the `Start()` function, so
    leave it alone for now.

docs/ML-Agents-Overview.md

@@ -347,7 +347,7 @@ rewards, which helps explain some of the training methods.
 
 In reinforcement learning, the end goal for the Agent is to discover a behavior
 (a Policy) that maximizes a reward. You will need to provide the agent one or
-more reward signals to use during training.Typically, a reward is defined by
+more reward signals to use during training. Typically, a reward is defined by
 your environment, and corresponds to reaching some goal. These are what we refer
 to as _extrinsic_ rewards, as they are defined external of the learning
 algorithm.

gym-unity/README.md

@@ -31,7 +31,7 @@ from the root of the project repository use:
 ```python
 from gym_unity.envs import UnityToGymWrapper
 
-env = UnityToGymWrapper(unity_environment, uint8_visual, allow_multiple_obs)
+env = UnityToGymWrapper(unity_environment, uint8_visual, flatten_branched, allow_multiple_obs)
 ```
 
 - `unity_environment` refers to the Unity environment to be wrapped.
@@ -46,7 +46,7 @@ env = UnityToGymWrapper(unity_environment, uint8_visual, allow_multiple_obs)
 
 - `allow_multiple_obs` will return a list of observations. The first elements contain the visual observations and the
   last element contains the array of vector observations. If False the environment returns a single array (containing
-  a single visual observations, if present, otherwise the vector observation)
+  a single visual observations, if present, otherwise the vector observation). Defaults to `False`.
 
 The returned environment `env` will function as a gym.