precommit hooks

README.md

@@ -22,7 +22,7 @@ If you just want to see the code for DEP, take a look at `deprl/dep_controller.p
 
 ### Big update!
 
-We now provide code for our newest preprint, [Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models](https://sites.google.com/view/naturalwalkingrl). With this work, we take a step towards _natural_ movement generation with RL. 
+We now provide code for our newest preprint, [Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models](https://sites.google.com/view/naturalwalkingrl). With this work, we take a step towards _natural_ movement generation with RL.
 This update provides code for adaptive energy costs in muscle-driven systems and provides support for the SCONE and Hyfydy softwares in the shape of the recently released [sconegym](https://github.com/tgeijten/sconegym/tree/main) environment suite.
 
 The new features also include pre-trained baselines from the preprint, enabling rendering from SCONE and much more. See the [docs](https://deprl.readthedocs.io/en/latest/?badge=latest) for more information.
@@ -61,7 +61,7 @@ We also collaborated with groups that provide musculoskeletal control environmen
 ### Hyfydy and sconegym
 We include several pre-trained baselines and configuration files to train the policies from our newest [preprint](https://arxiv.org/abs/2309.02976). These allow you to train walking agents in [Hyfydy](hyfydy.com) with RL for natural walking and robust running tasks. We worked together with Thomas Geijtenbeek [@tgeijten](https://github.com/tgeijten) to create a python environment interface for Hyfydy, called [sconegym](https://github.com/tgeijten/sconegym/tree/main)!
 This repository also includes the definitions of all the cost terms we used, see [here](https://github.com/tgeijten/sconegym/blob/main/sconegym/gaitgym.py).
-The configuration files to train our sconegym policies are included [here](https://github.com/martius-lab/depRL/tree/main/experiments/hyfydy). 
+The configuration files to train our sconegym policies are included [here](https://github.com/martius-lab/depRL/tree/main/experiments/hyfydy).
 
 
 Check out how to install sconegym from their [repo](https://github.com/tgeijten/sconegym/blob/main/sconegym/gaitgym.py), you can immediately start with a simple OpenSim model. To access the fast Hyfydy engine, and the complex 3D models, you need to request a trial license from the [Hyfydy](hyfydy.com) website or purchase a license. Some usage examples can be found [here](https://deprl.readthedocs.io/en/latest/hyfydy_baselines.html) and [here]()

examples/example_only_dep_myosuite.py

@@ -1,25 +1,20 @@
-import gym
-import myosuite
 import time
-from deprl import env_wrappers
-from deprl.dep_controller import DEP
 
+import gym
+import myosuite  # noqa
 
+from deprl import env_wrappers
+from deprl.dep_controller import DEP
 
-env = gym.make('myoLegWalk-v0')
+env = gym.make("myoLegWalk-v0")
 env = env_wrappers.GymWrapper(env)
 
-# You can also use SconeWrapper for Wrapper
-# env = env_wrappers.SconeWrapper(env)
 dep = DEP()
 dep.initialize(env.observation_space, env.action_space)
 
 env.reset()
 for i in range(1000):
-    action = dep.step(env.muscle_lengths())[0,:]
-    print(action.shape)
+    action = dep.step(env.muscle_lengths())[0, :]
     next_state, reward, done, _ = env.step(action)
-    time.sleep(0.01)
+    time.sleep(0.005)
     env.mj_render()
-
-

examples/example_only_dep_scone.py

@@ -1,11 +1,11 @@
 import gym
-import sconegym
+import sconegym  # noqa
+
 from deprl import env_wrappers
 from deprl.dep_controller import DEP
 
-
 # create the sconegym env
-env = gym.make('sconewalk_h2190-v1')
+env = gym.make("sconewalk_h2190-v1")
 
 # apply wrapper to environment
 env = env_wrappers.SconeWrapper(env)
@@ -28,7 +28,7 @@
 
     while True:
         # samples random action
-        action = dep.step(env.muscle_lengths())[0,:]
+        action = dep.step(env.muscle_lengths())[0, :]
         # applies action and advances environment by one step
         state, reward, done, info = env.step(action)
 
@@ -46,4 +46,3 @@
             break
 
 env.close()
-