Added DMC to docs

README.md

@@ -41,7 +41,7 @@ pip install .
 
 This will only install the basic classic control environments, which should run on most operating systems. For the full set of environments, use the install options:
 ```bash
-pip install -e .[box2d, brax, mario, dm_control]
+pip install -e .[box2d,brax,mario,dm_control]
 ```
 
 These may not be compatible with Windows systems. Box2D environment may need to be installed via conda on MacOS systems:

docs/source/environments/data/tab_overview_environments.csv

@@ -13,5 +13,9 @@ brax,CARLHumanoid,5,"Box(-1.0, 1.0, (17,), float32)","Box(-inf, inf, (304,), flo
 brax,CARLFetch,9,"Box(-1.0, 1.0, (10,), float32)","Box(-inf, inf, (110,), float32)"
 brax,CARLGrasp,9,"Box(-1.0, 1.0, (19,), float32)","Box(-inf, inf, (141,), float32)"
 brax,CARLUr5e,9,"Box(-1.0, 1.0, (6,), float32)","Box(-inf, inf, (75,), float32)"
+dmc,CARLDmcFishEnv,14,"Box(-1.0, 1.0, (5,), float64)","Box(-inf, inf, (24,), float32)"
+dmc,CARLDmcFingerEnv,18,"Box(-1.0, 1.0, (2,), float64)","Box(-inf, inf, (9,), float32)"
+dmc,CARLDmcQuadrupedEnv,14,"Box(-1.0, 1.1, (12,), float64)","Box(-inf, inf, (78,), float32)"
+dmc,CARLDmcWalkerEnv,14,"Box(-1.0, 1.0, (6,), float64)","Box(-inf, inf, (24,), float32)"
 RNA,CARLRnaDesignEnv,5,Discrete(4),"Box(-inf, inf, (11,), float32)"
 Mario,CARLMarioEnv,4,Discrete(10),"Box(0, 255, (4, 64, 64), uint8)"

docs/source/environments/environment_families/box2d.rst

@@ -25,9 +25,14 @@ CARL LunarLander Environment
 ------------------------------
 .. image:: ../data/screenshots/lunarlander.jpeg
     :width: 25%
-    :align: center
+    :align: left
     :alt: Screenshot of CARLLunarLanderEnv
 
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLLunarLanderEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
 Here, the lunar lander should be safely navigated to its landing pad.
 The lander's body, physics and simulation dynamics can be manipulated via the context features.
 

docs/source/environments/environment_families/classic_control.rst

@@ -9,9 +9,14 @@ CARL Pendulum Environment
 -------------------------
 .. image:: ../data/screenshots/pendulum.jpeg
     :width: 25%
-    :align: center
+    :align: left
     :alt: Pendulum Environment
 
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLPendulumEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
 In Pendulum, the agent's task is to swing up an inverted pendulum and
 balance it at the top from a random position. The action here is the
 direction and amount of force the agent wants to apply to the pendulum.
@@ -25,9 +30,14 @@ CARL CartPole Environment
 -------------------------
 .. image:: ../data/screenshots/cartpole.jpeg
     :width: 25%
-    :align: center
+    :align: left
     :alt: CartPole Environment
 
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLCartPoleEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
 CartPole, similarly to Pendulum, asks the agent to balance a pole upright, though
 this time the agent doesn't directly apply force to the pole but moves a cart on which
 the pole ist placed either to the left or the right.
@@ -41,9 +51,14 @@ CARL Acrobot Environment
 -------------------------
 .. image:: ../data/screenshots/acrobot.jpeg
     :width: 25%
-    :align: center
+    :align: left
     :alt: Acrobot Environment
 
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLAcrobotEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
 Acrobot is another swing-up task with the goal being swinging the end of the lower
 of two links up to a given height. The agent accomplishes this by actuating
 the joint connecting both links.
@@ -57,9 +72,14 @@ CARL MountainCar Environment
 ----------------------------
 .. image:: ../data/screenshots/mountaincar.jpeg
     :width: 25%
-    :align: center
+    :align: left
     :alt: MountainCar Environment
 
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLMountainCarEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
 The MountainCar environment asks the agent to move a car up a steep slope. In order
 to succeed, the agent has to accelerate using the opposite slope. There are two
 versions of the environment, a discrete one with only "left" and "right" as actions,

docs/source/environments/environment_families/dmc.rst

@@ -0,0 +1,81 @@
+CARL DMC Environments
+######################
+CARL includes the Finger, Fish, Quadruped and Walker environments from the `DeepMind Control Suite <https://github.com/deepmind/dm_control>`_.
+The context features control the MuJoCo physics engine, e.g. the floor friction.
+
+
+CARL DMC Finger Environment
+***************************
+.. image:: ../data/screenshots/finger.jpg
+  :width: 25%
+  :align: center
+  :alt: Screenshot of CARLDmcFinger
+
+
+The agent needs to learn to spin an object using the finger.
+
+
+.. csv-table:: Defaults and Bounds
+   :file: ../data/context_definitions/CARLDmcFinger.csv
+   :header-rows: 1
+
+
+
+CARL DMC Fish Environment
+**********************
+.. image:: ../data/screenshots/fish.jpg
+    :width: 25%
+    :height: 100px
+    :align: center
+    :alt: Screenshot of CARLDmcFish
+
+
+In Fish, the agent needs to swim as a simulated fish.
+
+
+.. csv-table:: Defaults and Bounds
+   :file: ../data/context_definitions/CARLDmcFish.csv
+   :header-rows: 1
+
+
+
+CARL DMC Quadruped Environment
+**********************
+.. image:: ../data/screenshots/quadruped.jpg
+    :width: 25%
+    :align: center
+    :alt: Screenshot of CARLDmcQuadruped
+
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLDmcQuadrupedEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
+
+The agent's goal is to walk efficiently with the quadruped robot.
+
+
+.. csv-table:: Defaults and Bounds
+   :file: ../data/context_definitions/CARLDmcQuadruped.csv
+   :header-rows: 1
+
+
+
+CARL DMC Walker Environment
+*****************************
+.. image:: ../data/screenshots/walker.jpg
+    :width: 25%
+    :align: left
+    :alt: Screenshot of CARLDmcWalker
+
+.. image:: ../data/context_generalization_plots/plot_ecdf_CARLDmcWalkerEnv.png
+    :width: 50%
+    :align: right
+    :alt: Influence of context settings on an agent trained on the default environment.
+
+The walker robot is supposed to move forward as fast as possible.
+
+
+.. csv-table:: Defaults and Bounds
+   :file: ../data/context_definitions/CARLDmcWalker.csv
+   :header-rows: 1

docs/source/environments/environment_families/index.rst

@@ -46,6 +46,15 @@ like joint strength or torso mass
 
     brax
 
+DeepMind Control Suite
+----
+Selected environment from the `DeepMind Control Suite <https://github.com/deepmind/dm_control>`_ with controllable physics.
+
+.. toctree::
+    :maxdepth: 2
+
+    dmc
+
 Mario
 -----
 `Super Mario (TOAD-GAN) <https://github.com/Mawiszus/TOAD-GAN>`_, a procedurally generated jump'n'run game with control