Merge branch 'fix_automatic_render' into pr_v0.3.0

.github/workflows/host_docs_static.yml

@@ -0,0 +1,40 @@
+name: Deploy static docs to Pages
+
+on:
+  push:
+    branches: ["release"]
+
+  # Allows you to run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
+# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
+concurrency:
+  group: "pages"
+  cancel-in-progress: false
+
+jobs:
+  # Single deploy job since we're just deploying
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Setup Pages
+        uses: actions/configure-pages@v4
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: 'docs/build/html'
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

fancy_gym/envs/mujoco/ant_jump/ant_jump.py

@@ -115,6 +115,7 @@ class AntJumpEnv(AntEnvCustomXML):
                          contact_force_range=contact_force_range,
                          reset_noise_scale=reset_noise_scale,
                          exclude_current_positions_from_observation=exclude_current_positions_from_observation, **kwargs)
+        self.render_active = False
 
     def step(self, action):
         self.current_step += 1
@@ -153,8 +154,15 @@ class AntJumpEnv(AntEnvCustomXML):
         }
         truncated = False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return obs, reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _get_obs(self):
         return np.append(super()._get_obs(), self.goal)
 

fancy_gym/envs/mujoco/beerpong/beerpong.py

@@ -44,6 +44,7 @@ class BeerPongEnv(MujocoEnv, utils.EzPickle):
     }
 
     def __init__(self, **kwargs):
+        utils.EzPickle.__init__(self)
         self._steps = 0
         # Small Context -> Easier. Todo: Should we do different versions?
         # self.xml_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "assets", "beerpong_wo_cup.xml")
@@ -89,7 +90,7 @@ class BeerPongEnv(MujocoEnv, utils.EzPickle):
             observation_space=self.observation_space,
             **kwargs
         )
-        utils.EzPickle.__init__(self)
+        self.render_active = False
 
     @property
     def start_pos(self):
@@ -169,8 +170,15 @@ class BeerPongEnv(MujocoEnv, utils.EzPickle):
 
         truncated = False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return ob, reward, terminated, truncated, infos
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _get_obs(self):
         theta = self.data.qpos.flat[:7].copy()
         theta_dot = self.data.qvel.flat[:7].copy()

fancy_gym/envs/mujoco/box_pushing/box_pushing_env.py

@@ -4,6 +4,7 @@ import numpy as np
 from gymnasium import utils, spaces
 from gymnasium.envs.mujoco import MujocoEnv
 from fancy_gym.envs.mujoco.box_pushing.box_pushing_utils import rot_to_quat, get_quaternion_error, rotation_distance
+from fancy_gym.envs.mujoco.box_pushing.box_pushing_utils import rot_to_quat, get_quaternion_error, rotation_distance
 from fancy_gym.envs.mujoco.box_pushing.box_pushing_utils import q_max, q_min, q_dot_max, q_torque_max
 from fancy_gym.envs.mujoco.box_pushing.box_pushing_utils import desired_rod_quat
 
@@ -60,6 +61,7 @@ class BoxPushingEnvBase(MujocoEnv, utils.EzPickle):
                            frame_skip=self.frame_skip,
                            observation_space=self.observation_space, **kwargs)
         self.action_space = spaces.Box(low=-1, high=1, shape=(7,))
+        self.render_active = False
 
     def step(self, action):
         action = 10 * np.clip(action, self.action_space.low, self.action_space.high)
@@ -108,8 +110,15 @@ class BoxPushingEnvBase(MujocoEnv, utils.EzPickle):
         terminated = episode_end and infos['is_success']
         truncated = episode_end and not infos['is_success']
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return obs, reward, terminated, truncated, infos
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def reset_model(self):
         # rest box to initial position
         self.set_state(self.init_qpos_box_pushing, self.init_qvel_box_pushing)

fancy_gym/envs/mujoco/half_cheetah_jump/half_cheetah_jump.py

@@ -60,7 +60,11 @@ class HalfCheetahEnvCustomXML(HalfCheetahEnv):
             default_camera_config=DEFAULT_CAMERA_CONFIG,
             **kwargs,
         )
+        self.render_active = False
 
+    def render(self):
+        self.render_active = True
+        return super().render()
 
 class HalfCheetahJumpEnv(HalfCheetahEnvCustomXML):
     """
@@ -120,6 +124,9 @@ class HalfCheetahJumpEnv(HalfCheetahEnvCustomXML):
             'max_height': self.max_height
         }
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
     def _get_obs(self):

fancy_gym/envs/mujoco/hopper_jump/hopper_jump.py

@@ -88,6 +88,12 @@ class HopperEnvCustomXML(HopperEnv):
             **kwargs,
         )
 
+        self.render_active = False
+
+    def render(self):
+        self.render_active = True
+        return super().render()
+
 
 class HopperJumpEnv(HopperEnvCustomXML):
     """
@@ -201,6 +207,10 @@ class HopperJumpEnv(HopperEnvCustomXML):
             healthy=self.is_healthy,
             contact_dist=self.contact_dist or 0
         )
+
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
     def _get_obs(self):

fancy_gym/envs/mujoco/hopper_jump/hopper_jump_on_box.py

@@ -140,6 +140,9 @@ class HopperJumpOnBoxEnv(HopperEnvCustomXML):
 
         truncated = self.current_step >= self.max_episode_steps and not terminated
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
     def _get_obs(self):

fancy_gym/envs/mujoco/hopper_throw/hopper_throw.py

@@ -61,6 +61,8 @@ class HopperThrowEnv(HopperEnvCustomXML):
                          exclude_current_positions_from_observation=exclude_current_positions_from_observation,
                          **kwargs)
 
+        self.render_active = False
+
     def step(self, action):
         self.current_step += 1
         self.do_simulation(action, self.frame_skip)
@@ -94,8 +96,15 @@ class HopperThrowEnv(HopperEnvCustomXML):
         }
         truncated = False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _get_obs(self):
         return np.append(super()._get_obs(), self.goal)
 

fancy_gym/envs/mujoco/hopper_throw/hopper_throw_in_basket.py

@@ -68,6 +68,7 @@ class HopperThrowInBasketEnv(HopperEnvCustomXML):
                          reset_noise_scale=reset_noise_scale,
                          exclude_current_positions_from_observation=exclude_current_positions_from_observation,
                          **kwargs)
+        self.render_active = False
 
     def step(self, action):
 
@@ -118,8 +119,15 @@ class HopperThrowInBasketEnv(HopperEnvCustomXML):
         }
         truncated = False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _get_obs(self):
         return np.append(super()._get_obs(), self.basket_x)
 

fancy_gym/envs/mujoco/reacher/reacher.py

@@ -47,6 +47,8 @@ class ReacherEnv(MujocoEnv, utils.EzPickle):
                            **kwargs
                            )
 
+        self.render_active = False
+
     def step(self, action):
         self._steps += 1
 
@@ -77,8 +79,15 @@ class ReacherEnv(MujocoEnv, utils.EzPickle):
             goal=self.goal if hasattr(self, "goal") else None
         )
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return ob, reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def distance_reward(self):
         vec = self.get_body_com("fingertip") - self.get_body_com("target")
         return -self._reward_weight * np.linalg.norm(vec)

fancy_gym/envs/mujoco/table_tennis/table_tennis_env.py

@@ -71,6 +71,8 @@ class TableTennisEnv(MujocoEnv, utils.EzPickle):
                            observation_space=self.observation_space,
                            **kwargs)
 
+        self.render_active = False
+
         if ctxt_dim == 2:
             self.context_bounds = CONTEXT_BOUNDS_2DIMS
         elif ctxt_dim == 4:
@@ -158,8 +160,15 @@ class TableTennisEnv(MujocoEnv, utils.EzPickle):
 
         terminated, truncated = self._terminated, False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return self._get_obs(), reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _contact_checker(self, id_1, id_2):
         for coni in range(0, self.data.ncon):
             con = self.data.contact[coni]

fancy_gym/envs/mujoco/walker_2d_jump/walker_2d_jump.py

@@ -79,6 +79,8 @@ class Walker2dEnvCustomXML(Walker2dEnv):
             **kwargs,
         )
 
+        self.render_active = False
+
 
 class Walker2dJumpEnv(Walker2dEnvCustomXML):
     """
@@ -145,8 +147,15 @@ class Walker2dJumpEnv(Walker2dEnvCustomXML):
         }
         truncated = False
 
+        if self.render_active and self.render_mode=='human':
+            self.render()
+
         return observation, reward, terminated, truncated, info
 
+    def render(self):
+        self.render_active = True
+        return super().render()
+
     def _get_obs(self):
         return np.append(super()._get_obs(), self.goal)