dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master'

Browse Source 
# Conflicts:
#	alr_envs/__init__.py
#	alr_envs/alr/classic_control/hole_reacher/hole_reacher.py
#	alr_envs/utils/mps/mp_wrapper.py
This commit is contained in:
ottofabian
2021-09-29 16:18:37 +02:00
parent ed75d565e2 c1dfb583fe
commit 8d1530823c
205 changed files with 3929 additions and 1741 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alr_envs/alr/mujoco/reacher/__init__.py
View File
alr_envs/alr/mujoco/reacher/alr_reacher.py
+106
View File
@@ -0,0 +1,106 @@
import os
import numpy as np
from gym import utils
from gym.envs.mujoco import MujocoEnv
import alr_envs.utils.utils as alr_utils
class ALRReacherEnv(MujocoEnv, utils.EzPickle):
def __init__(self, steps_before_reward=200, n_links=5, balance=False):
utils.EzPickle.__init__(**locals())
self._steps = 0
self.steps_before_reward = steps_before_reward
self.n_links = n_links
self.balance = balance
self.balance_weight = 1.0
self.reward_weight = 1
if steps_before_reward == 200:
self.reward_weight = 200
elif steps_before_reward == 50:
self.reward_weight = 50
if n_links == 5:
file_name = 'reacher_5links.xml'
elif n_links == 7:
file_name = 'reacher_7links.xml'
else:
raise ValueError(f"Invalid number of links {n_links}, only 5 or 7 allowed.")
MujocoEnv.__init__(self, os.path.join(os.path.dirname(__file__), "assets", file_name), 2)
def step(self, a):
self._steps += 1
reward_dist = 0.0
angular_vel = 0.0
reward_balance = 0.0
if self._steps >= self.steps_before_reward:
vec = self.get_body_com("fingertip") - self.get_body_com("target")
reward_dist -= self.reward_weight * np.linalg.norm(vec)
angular_vel -= np.linalg.norm(self.sim.data.qvel.flat[:self.n_links])
reward_ctrl = - np.square(a).sum()
if self.balance:
reward_balance -= self.balance_weight * np.abs(
alr_utils.angle_normalize(np.sum(self.sim.data.qpos.flat[:self.n_links]), type="rad"))
reward = reward_dist + reward_ctrl + angular_vel + reward_balance
self.do_simulation(a, self.frame_skip)
ob = self._get_obs()
done = False
return ob, reward, done, dict(reward_dist=reward_dist, reward_ctrl=reward_ctrl,
velocity=angular_vel, reward_balance=reward_balance,
end_effector=self.get_body_com("fingertip").copy(),
goal=self.goal if hasattr(self, "goal") else None)
def viewer_setup(self):
self.viewer.cam.trackbodyid = 0
def reset_model(self):
qpos = self.np_random.uniform(low=-0.1, high=0.1, size=self.model.nq) + self.init_qpos
while True:
self.goal = self.np_random.uniform(low=-self.n_links / 10, high=self.n_links / 10, size=2)
if np.linalg.norm(self.goal) < self.n_links / 10:
break
qpos[-2:] = self.goal
qvel = self.init_qvel + self.np_random.uniform(low=-.005, high=.005, size=self.model.nv)
qvel[-2:] = 0
self.set_state(qpos, qvel)
self._steps = 0
return self._get_obs()
def _get_obs(self):
theta = self.sim.data.qpos.flat[:self.n_links]
return np.concatenate([
np.cos(theta),
np.sin(theta),
self.sim.data.qpos.flat[self.n_links:], # this is goal position
self.sim.data.qvel.flat[:self.n_links], # this is angular velocity
self.get_body_com("fingertip") - self.get_body_com("target"),
# self.get_body_com("target"), # only return target to make problem harder
[self._steps],
])
if __name__ == '__main__':
nl = 5
render_mode = "human" # "human" or "partial" or "final"
env = ALRReacherEnv(n_links=nl)
obs = env.reset()
for i in range(2000):
# objective.load_result("/tmp/cma")
# test with random actions
ac = env.action_space.sample()
obs, rew, d, info = env.step(ac)
if i % 10 == 0:
env.render(mode=render_mode)
if d:
env.reset()
env.close()
alr_envs/alr/mujoco/reacher/assets/reacher_5links.xml
+54
View File
@@ -0,0 +1,54 @@
<mujoco model="reacher">
<compiler angle="radian" inertiafromgeom="true"/>
<default>
<joint armature="1" damping="1" limited="true"/>
<geom contype="0" friction="1 0.1 0.1" rgba="0.7 0.7 0 1"/>
</default>
<option gravity="0 0 -9.81" integrator="RK4" timestep="0.01"/>
<worldbody>
<!-- Arena -->
<geom conaffinity="0" contype="0" name="ground" pos="0 0 0" rgba="0.9 0.9 0.9 1" size="1 1 10" type="plane"/>
<geom conaffinity="0" fromto="-.6 -.6 .01 .6 -.6 .01" name="sideS" rgba="0.9 0.4 0.6 1" size=".02" type="capsule"/>
<geom conaffinity="0" fromto=" .6 -.6 .01 .6 .6 .01" name="sideE" rgba="0.9 0.4 0.6 1" size=".02" type="capsule"/>
<geom conaffinity="0" fromto="-.6 .6 .01 .6 .6 .01" name="sideN" rgba="0.9 0.4 0.6 1" size=".02" type="capsule"/>
<geom conaffinity="0" fromto="-.6 -.6 .01 -.6 .6 .01" name="sideW" rgba="0.9 0.4 0.6 1" size=".02" type="capsule"/>
<!-- Arm -->
<geom conaffinity="0" contype="0" fromto="0 0 0 0 0 0.02" name="root" rgba="0.9 0.4 0.6 1" size=".011" type="cylinder"/>
<body name="body0" pos="0 0 .01">
<geom fromto="0 0 0 0.1 0 0" name="link0" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<joint axis="0 0 1" limited="false" name="joint0" pos="0 0 0" type="hinge"/>
<body name="body1" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint1" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link1" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body2" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint2" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link2" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body3" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint3" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link3" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body4" pos="0.1 0 0">
<joint axis="0 0 1" limited="true" name="joint4" pos="0 0 0" range="-3.0 3.0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link4" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="fingertip" pos="0.11 0 0">
<geom contype="0" name="fingertip" pos="0 0 0" rgba="0.0 0.8 0.6 1" size=".01" type="sphere"/>
</body>
</body>
</body>
</body>
</body>
</body>
<!-- Target -->
<body name="target" pos=".1 -.1 .01">
<joint armature="0" axis="1 0 0" damping="0" limited="true" name="target_x" pos="0 0 0" range="-.27 .27" ref=".1" stiffness="0" type="slide"/>
<joint armature="0" axis="0 1 0" damping="0" limited="true" name="target_y" pos="0 0 0" range="-.27 .27" ref="-.1" stiffness="0" type="slide"/>
<geom conaffinity="0" contype="0" name="target" pos="0 0 0" rgba="0.9 0.2 0.2 1" size=".009" type="sphere"/>
</body>
</worldbody>
<actuator>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint0"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint1"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint2"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint3"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint4"/>
</actuator>
</mujoco>
alr_envs/alr/mujoco/reacher/assets/reacher_7links.xml
+75
View File
@@ -0,0 +1,75 @@
<mujoco model="reacher">
<compiler angle="radian" inertiafromgeom="true"/>
<default>
<joint armature="1" damping="1" limited="true"/>
<geom contype="0" friction="1 0.1 0.1" rgba="0.7 0.7 0 1"/>
</default>
<option gravity="0 0 -9.81" integrator="RK4" timestep="0.01"/>
<worldbody>
<!-- Arena -->
<geom conaffinity="0" contype="0" name="ground" pos="0 0 0" rgba="0.9 0.9 0.9 1" size="1 1 10" type="plane"/>
<geom conaffinity="0" fromto="-.8 -.8 .01 .8 -.8 .01" name="sideS" rgba="0.9 0.4 0.6 1" size=".02"
type="capsule"/>
<geom conaffinity="0" fromto=" .8 -.8 .01 .8 .8 .01" name="sideE" rgba="0.9 0.4 0.6 1" size=".02"
type="capsule"/>
<geom conaffinity="0" fromto="-.8 .8 .01 .8 .8 .01" name="sideN" rgba="0.9 0.4 0.6 1" size=".02"
type="capsule"/>
<geom conaffinity="0" fromto="-.8 -.8 .01 -.8 .8 .01" name="sideW" rgba="0.9 0.4 0.6 1" size=".02"
type="capsule"/>
<!-- Arm -->
<geom conaffinity="0" contype="0" fromto="0 0 0 0 0 0.02" name="root" rgba="0.9 0.4 0.6 1" size=".011"
type="cylinder"/>
<body name="body0" pos="0 0 .01">
<geom fromto="0 0 0 0.1 0 0" name="link0" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<joint axis="0 0 1" limited="false" name="joint0" pos="0 0 0" type="hinge"/>
<body name="body1" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint1" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link1" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body2" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint2" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link2" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body3" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint3" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link3" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body4" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint4" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link4" rgba="0.0 0.4 0.6 1" size=".01" type="capsule"/>
<body name="body5" pos="0.1 0 0">
<joint axis="0 0 1" limited="false" name="joint5" pos="0 0 0" type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link5" rgba="0.0 0.4 0.6 1" size=".01"
type="capsule"/>
<body name="body6" pos="0.1 0 0">
<joint axis="0 0 1" limited="true" name="joint6" pos="0 0 0" range="-3.0 3.0"
type="hinge"/>
<geom fromto="0 0 0 0.1 0 0" name="link6" rgba="0.0 0.4 0.6 1" size=".01"
type="capsule"/>
<body name="fingertip" pos="0.11 0 0">
<geom contype="0" name="fingertip" pos="0 0 0" rgba="0.0 0.8 0.6 1" size=".01"
type="sphere"/>
</body>
</body>
</body>
</body>
</body>
</body>
</body>
</body>
<!-- Target -->
<body name="target" pos=".1 -.1 .01">
<joint armature="0" axis="1 0 0" damping="0" limited="true" name="target_x" pos="0 0 0" range="-.27 .27"
ref=".1" stiffness="0" type="slide"/>
<joint armature="0" axis="0 1 0" damping="0" limited="true" name="target_y" pos="0 0 0" range="-.27 .27"
ref="-.1" stiffness="0" type="slide"/>
<geom conaffinity="0" contype="0" name="target" pos="0 0 0" rgba="0.9 0.2 0.2 1" size=".009" type="sphere"/>
</body>
</worldbody>
<actuator>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint0"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint1"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint2"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint3"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint4"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint5"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="200.0" joint="joint6"/>
</actuator>
</mujoco>
alr_envs/alr/mujoco/reacher/balancing.py
+53
View File
@@ -0,0 +1,53 @@
import os
import numpy as np
from gym import utils
from gym.envs.mujoco import mujoco_env
import alr_envs.utils.utils as alr_utils
class BalancingEnv(mujoco_env.MujocoEnv, utils.EzPickle):
def __init__(self, n_links=5):
utils.EzPickle.__init__(**locals())
self.n_links = n_links
if n_links == 5:
file_name = 'reacher_5links.xml'
elif n_links == 7:
file_name = 'reacher_7links.xml'
else:
raise ValueError(f"Invalid number of links {n_links}, only 5 or 7 allowed.")
mujoco_env.MujocoEnv.__init__(self, os.path.join(os.path.dirname(__file__), "assets", file_name), 2)
def step(self, a):
angle = alr_utils.angle_normalize(np.sum(self.sim.data.qpos.flat[:self.n_links]), type="rad")
reward = - np.abs(angle)
self.do_simulation(a, self.frame_skip)
ob = self._get_obs()
done = False
return ob, reward, done, dict(angle=angle, end_effector=self.get_body_com("fingertip").copy())
def viewer_setup(self):
self.viewer.cam.trackbodyid = 1
def reset_model(self):
# This also generates a goal, we however do not need/use it
qpos = self.np_random.uniform(low=-0.1, high=0.1, size=self.model.nq) + self.init_qpos
qpos[-2:] = 0
qvel = self.init_qvel + self.np_random.uniform(low=-.005, high=.005, size=self.model.nv)
qvel[-2:] = 0
self.set_state(qpos, qvel)
return self._get_obs()
def _get_obs(self):
theta = self.sim.data.qpos.flat[:self.n_links]
return np.concatenate([
np.cos(theta),
np.sin(theta),
self.sim.data.qvel.flat[:self.n_links], # this is angular velocity
])