Update README.md

Author: ossamaAhmed

README.md

@@ -282,7 +282,7 @@ env.close()
   ```
 
 ## Curriculum Through Interventions
-To provide a convenient way of specifying learning curricula, we introduce intervention actors.  At each time step, such an actor takes all the exposed variables of the environ-ment as inputs and may intervene on them.  To encourage modularity, one may combine multipleactors in a learning curriculum.  This actor is defined by the episode number to start intervening,the episode number to stop intervening, the timestep within the episode it should intervene and theepisode periodicity of interventions.  
+To provide a convenient way of specifying learning curricula, we introduce intervention actors.  At each time step, such an actor takes all the exposed variables of the environment as inputs and may intervene on them.  To encourage modularity, one may combine multiple actors in a learning curriculum.  This actor is defined by the episode number to start intervening,the episode number to stop intervening, the time step within the episode it should intervene and the episode periodicity of interventions.  
 <p align=center>
 <img src="docs/media/guided_goal.gif" width=200><img src="docs/media/block_interventions.gif" width=200>
 </p>

docs/guide/task_setups.rst

@@ -149,6 +149,7 @@ structured: In this mode the observation space is a lower-dimensional feature ve
 time left for task (1), joint_positions (9), joint_velocities (9), end_effector_positions (9). Then for each tool object in the
 environment additional 17-dimensions are used representing: type (1), size (3), cartesian_position (3),
 quaternion_orientation (4), linear_velocity (3), angular_velocity (3). For each goal subshape in the environment additional
+11-dimesnions are used representing: type (1), size (3), cartesian_position (3) and orientation (4). Lastly, if there are any fixed blocks in the environment additional
 11-dimesnions are used representing: type (1), size (3), cartesian_position (3) and orientation (4).
 
 .. image:: ../media/structured_observation_space.png

docs/modules/actors/actors.rst

@@ -16,3 +16,54 @@ BaseActorPolicy
     :members:
 
      .. automethod:: __init__
+
+PushingActorPolicy
+-------------------
+.. autoclass:: PushingActorPolicy
+    :members:
+
+     .. automethod:: __init__
+
+
+PickingActorPolicy
+------------------
+.. autoclass:: PickingActorPolicy
+    :members:
+
+     .. automethod:: __init__
+
+
+PickAndPlaceActorPolicy
+-----------------------
+.. autoclass:: PickAndPlaceActorPolicy
+    :members:
+
+     .. automethod:: __init__
+
+Stacking2ActorPolicy
+--------------------
+.. autoclass:: Stacking2ActorPolicy
+    :members:
+
+     .. automethod:: __init__
+
+ReacherActorPolicy
+--------------------
+.. autoclass:: ReacherActorPolicy
+    :members:
+
+     .. automethod:: __init__
+
+GraspingPolicy
+---------------
+.. autoclass:: GraspingPolicy
+    :members:
+
+     .. automethod:: __init__
+
+RandomActorPolicy
+-----------------
+.. autoclass:: RandomActorPolicy
+    :members:
+
+     .. automethod:: __init__

docs/modules/sim2real/sim2real.rst

@@ -9,3 +9,10 @@ RealisticRobotWrapper
     :members:
 
     .. automethod:: __init__
+
+TransferRealWrapper
+-------------------
+.. autoclass:: TransferReal
+    :members:
+
+    .. automethod:: __init__

docs/modules/task_generators/task_generators.rst

@@ -4,7 +4,7 @@ Task Generators
 Task
 ----
 .. automodule:: causal_world.task_generators.task
-    :members: task_generator
+    :members: generate_task
 
 .. automodule:: causal_world.task_generators