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

renameing alr module and updating tests

Browse Source
This commit is contained in:
Fabian
2022-07-12 15:17:02 +02:00
parent 79c26681c9
commit 0339361656
127 changed files with 418 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alr_envs/alr/mujoco/reacher/__init__.py
-1
View File
@@ -1 +0,0 @@
from .mp_wrapper import MPWrapper
alr_envs/alr/mujoco/reacher/assets/reacher_5links.xml
-57
View File
@@ -1,57 +0,0 @@
<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"/>-->
<joint armature="0" axis="1 0 0" damping="0" limited="true" name="target_x" pos="0 0 0" range="-.7 .7" 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="-.7 .7" 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>
<site name="context_space" pos="0 0.0 0.0" euler="0 0 0" size="0.5 0.5 0.01" rgba="0 1 0 0.1" type="box"/>
</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
@@ -1,75 +0,0 @@
<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/mp_wrapper.py
-27
View File
@@ -1,27 +0,0 @@
from typing import Union, Tuple
import gym
import numpy as np
from alr_envs.black_box.raw_interface_wrapper import RawInterfaceWrapper
class MPWrapper(RawInterfaceWrapper):
@property
def context_mask(self):
return np.concatenate([[False] * self.env.n_links, # cos
[False] * self.env.n_links, # sin
[True] * 2, # goal position
[False] * self.env.n_links, # angular velocity
[False] * 3, # goal distance
# [False], # step
])
@property
def current_pos(self) -> Union[float, int, np.ndarray, Tuple]:
return self.env.data.qpos.flat[:self.env.n_links]
@property
def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
return self.env.data.qvel.flat[:self.env.n_links]
alr_envs/alr/mujoco/reacher/reacher.py
-105
View File
@@ -1,105 +0,0 @@
import os
import numpy as np
from gym import utils
from gym.envs.mujoco import MujocoEnv
class ReacherEnv(MujocoEnv, utils.EzPickle):
"""
More general version of the gym mujoco Reacher environment
"""
def __init__(self, sparse: bool = False, n_links: int = 5, ctrl_cost_weight: int = 1):
utils.EzPickle.__init__(**locals())
self._steps = 0
self.n_links = n_links
self.ctrl_cost_weight = ctrl_cost_weight
self.sparse = sparse
self.reward_weight = 1 if not sparse else 200
file_name = f'reacher_{n_links}links.xml'
MujocoEnv.__init__(self, os.path.join(os.path.dirname(__file__), "assets", file_name), 2)
def step(self, action):
self._steps += 1
is_reward = not self.sparse or (self.sparse and self._steps == 200)
reward_dist = 0.0
angular_vel = 0.0
if is_reward:
reward_dist = self.distance_reward()
angular_vel = self.velocity_reward()
reward_ctrl = -self.ctrl_cost_weight * np.square(action).sum()
reward = reward_dist + reward_ctrl + angular_vel
self.do_simulation(action, self.frame_skip)
ob = self._get_obs()
done = False
infos = dict(
reward_dist=reward_dist,
reward_ctrl=reward_ctrl,
velocity=angular_vel,
end_effector=self.get_body_com("fingertip").copy(),
goal=self.goal if hasattr(self, "goal") else None
)
return ob, reward, done, infos
def distance_reward(self):
vec = self.get_body_com("fingertip") - self.get_body_com("target")
return -self.reward_weight * np.linalg.norm(vec)
def velocity_reward(self):
return -10 * np.square(self.data.qvel.flat[:self.n_links]).sum() if self.sparse else 0.0
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.copy()
)
while True:
# full space
self.goal = self.np_random.uniform(low=-self.n_links / 10, high=self.n_links / 10, size=2)
# I Quadrant
# self.goal = self.np_random.uniform(low=0, high=self.n_links / 10, size=2)
# II Quadrant
# self.goal = np.random.uniform(low=[-self.n_links / 10, 0], high=[0, self.n_links / 10], size=2)
# II + III Quadrant
# self.goal = np.random.uniform(low=-self.n_links / 10, high=[0, self.n_links / 10], size=2)
# I + II Quadrant
# self.goal = np.random.uniform(low=[-self.n_links / 10, 0], high=self.n_links, size=2)
if np.linalg.norm(self.goal) < self.n_links / 10:
break
qpos[-2:] = self.goal
qvel = (
# self.np_random.uniform(low=-0.005, high=0.005, size=self.model.nv) +
self.init_qvel.copy()
)
qvel[-2:] = 0
self.set_state(qpos, qvel)
self._steps = 0
return self._get_obs()
def _get_obs(self):
theta = self.data.qpos.flat[:self.n_links]
target = self.get_body_com("target")
return np.concatenate([
np.cos(theta),
np.sin(theta),
target[:2], # x-y of goal position
self.data.qvel.flat[:self.n_links], # angular velocity
self.get_body_com("fingertip") - target, # goal distance
])