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

Added environments from Paul + Marc

Browse Source
This commit is contained in:
Onur
2022-04-13 17:28:25 +02:00
parent 7ffe94dcfd
commit 092525889b
26 changed files with 1795 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alr_envs/alr/mujoco/half_cheetah_jump/__init__.py
+1
View File
@@ -0,0 +1 @@
from .mp_wrapper import MPWrapper
alr_envs/alr/mujoco/half_cheetah_jump/assets/cheetah.xml
+62
View File
@@ -0,0 +1,62 @@
<mujoco model="cheetah">
<compiler angle="radian" coordinate="local" inertiafromgeom="true" settotalmass="14"/>
<default>
<joint armature=".1" damping=".01" limited="true" solimplimit="0 .8 .03" solreflimit=".02 1" stiffness="8"/>
<geom conaffinity="0" condim="3" contype="1" friction=".4 .1 .1" rgba="0.8 0.6 .4 1" solimp="0.0 0.8 0.01" solref="0.02 1"/>
<motor ctrllimited="true" ctrlrange="-1 1"/>
</default>
<size nstack="300000" nuser_geom="1"/>
<option gravity="0 0 -9.81" timestep="0.01"/>
<asset>
<texture builtin="gradient" height="100" rgb1="1 1 1" rgb2="0 0 0" type="skybox" width="100"/>
<texture builtin="flat" height="1278" mark="cross" markrgb="1 1 1" name="texgeom" random="0.01" rgb1="0.8 0.6 0.4" rgb2="0.8 0.6 0.4" type="cube" width="127"/>
<texture builtin="checker" height="100" name="texplane" rgb1="0 0 0" rgb2="0.8 0.8 0.8" type="2d" width="100"/>
<material name="MatPlane" reflectance="0.5" shininess="1" specular="1" texrepeat="60 60" texture="texplane"/>
<material name="geom" texture="texgeom" texuniform="true"/>
</asset>
<worldbody>
<light cutoff="100" diffuse="1 1 1" dir="-0 0 -1.3" directional="true" exponent="1" pos="0 0 1.3" specular=".1 .1 .1"/>
<geom conaffinity="1" condim="3" material="MatPlane" name="floor" pos="0 0 0" rgba="0.8 0.9 0.8 1" size="40 40 40" type="plane"/>
<body name="torso" pos="0 0 .7">
<camera name="track" mode="trackcom" pos="0 -3 0.3" xyaxes="1 0 0 0 0 1"/>
<joint armature="0" axis="1 0 0" damping="0" limited="false" name="rootx" pos="0 0 0" stiffness="0" type="slide"/>
<joint armature="0" axis="0 0 1" damping="0" limited="false" name="rootz" pos="0 0 0" stiffness="0" type="slide"/>
<joint armature="0" axis="0 1 0" damping="0" limited="false" name="rooty" pos="0 0 0" stiffness="0" type="hinge"/>
<geom fromto="-.5 0 0 .5 0 0" name="torso" size="0.046" type="capsule"/>
<geom axisangle="0 1 0 .87" name="head" pos=".6 0 .1" size="0.046 .15" type="capsule"/>
<!-- <site name='tip' pos='.15 0 .11'/>-->
<body name="bthigh" pos="-.5 0 0">
<joint axis="0 1 0" damping="6" name="bthigh" pos="0 0 0" range="-.52 1.05" stiffness="240" type="hinge"/>
<geom axisangle="0 1 0 -3.8" name="bthigh" pos=".1 0 -.13" size="0.046 .145" type="capsule"/>
<body name="bshin" pos=".16 0 -.25">
<joint axis="0 1 0" damping="4.5" name="bshin" pos="0 0 0" range="-.785 .785" stiffness="180" type="hinge"/>
<geom axisangle="0 1 0 -2.03" name="bshin" pos="-.14 0 -.07" rgba="0.9 0.6 0.6 1" size="0.046 .15" type="capsule"/>
<body name="bfoot" pos="-.28 0 -.14">
<joint axis="0 1 0" damping="3" name="bfoot" pos="0 0 0" range="-.4 .785" stiffness="120" type="hinge"/>
<geom axisangle="0 1 0 -.27" name="bfoot" pos=".03 0 -.097" rgba="0.9 0.6 0.6 1" size="0.046 .094" type="capsule"/>
</body>
</body>
</body>
<body name="fthigh" pos=".5 0 0">
<joint axis="0 1 0" damping="4.5" name="fthigh" pos="0 0 0" range="-1 .7" stiffness="180" type="hinge"/>
<geom axisangle="0 1 0 .52" name="fthigh" pos="-.07 0 -.12" size="0.046 .133" type="capsule"/>
<body name="fshin" pos="-.14 0 -.24">
<joint axis="0 1 0" damping="3" name="fshin" pos="0 0 0" range="-1.2 .87" stiffness="120" type="hinge"/>
<geom axisangle="0 1 0 -.6" name="fshin" pos=".065 0 -.09" rgba="0.9 0.6 0.6 1" size="0.046 .106" type="capsule"/>
<body name="ffoot" pos=".13 0 -.18">
<joint axis="0 1 0" damping="1.5" name="ffoot" pos="0 0 0" range="-.5 .5" stiffness="60" type="hinge"/>
<geom axisangle="0 1 0 -.6" name="ffoot" pos=".045 0 -.07" rgba="0.9 0.6 0.6 1" size="0.046 .07" type="capsule"/>
</body>
</body>
</body>
</body>
</worldbody>
<actuator>
<motor gear="120" joint="bthigh" name="bthigh"/>
<motor gear="90" joint="bshin" name="bshin"/>
<motor gear="60" joint="bfoot" name="bfoot"/>
<motor gear="120" joint="fthigh" name="fthigh"/>
<motor gear="60" joint="fshin" name="fshin"/>
<motor gear="30" joint="ffoot" name="ffoot"/>
</actuator>
</mujoco>
alr_envs/alr/mujoco/half_cheetah_jump/half_cheetah_jump.py
+100
View File
@@ -0,0 +1,100 @@
import os
from gym.envs.mujoco.half_cheetah_v3 import HalfCheetahEnv
import numpy as np
MAX_EPISODE_STEPS_HALFCHEETAHJUMP = 100
class ALRHalfCheetahJumpEnv(HalfCheetahEnv):
"""
ctrl_cost_weight 0.1 -> 0.0
"""
def __init__(self,
xml_file='cheetah.xml',
forward_reward_weight=1.0,
ctrl_cost_weight=0.0,
reset_noise_scale=0.1,
context=True,
exclude_current_positions_from_observation=True,
max_episode_steps=100):
self.current_step = 0
self.max_height = 0
self.max_episode_steps = max_episode_steps
self.goal = 0
self.context = context
xml_file = os.path.join(os.path.dirname(__file__), "assets", xml_file)
super().__init__(xml_file, forward_reward_weight, ctrl_cost_weight, reset_noise_scale,
exclude_current_positions_from_observation)
def step(self, action):
self.current_step += 1
self.do_simulation(action, self.frame_skip)
height_after = self.get_body_com("torso")[2]
self.max_height = max(height_after, self.max_height)
## Didnt use fell_over, because base env also has no done condition - Paul and Marc
# fell_over = abs(self.sim.data.qpos[2]) > 2.5 # how to figure out if the cheetah fell over? -> 2.5 oke?
# TODO: Should a fall over be checked herE?
done = False
ctrl_cost = self.control_cost(action)
costs = ctrl_cost
if self.current_step == self.max_episode_steps:
height_goal_distance = -10*np.linalg.norm(self.max_height - self.goal) + 1e-8 if self.context \
else self.max_height
rewards = self._forward_reward_weight * height_goal_distance
else:
rewards = 0
observation = self._get_obs()
reward = rewards - costs
info = {
'height': height_after,
'max_height': self.max_height
}
return observation, reward, done, info
def _get_obs(self):
return np.append(super()._get_obs(), self.goal)
def reset(self):
self.max_height = 0
self.current_step = 0
self.goal = np.random.uniform(1.1, 1.6, 1) # 1.1 1.6
return super().reset()
# overwrite reset_model to make it deterministic
def reset_model(self):
noise_low = -self._reset_noise_scale
noise_high = self._reset_noise_scale
qpos = self.init_qpos # + self.np_random.uniform(low=noise_low, high=noise_high, size=self.model.nq)
qvel = self.init_qvel # + self.np_random.uniform(low=noise_low, high=noise_high, size=self.model.nv)
self.set_state(qpos, qvel)
observation = self._get_obs()
return observation
if __name__ == '__main__':
render_mode = "human" # "human" or "partial" or "final"
env = ALRHalfCheetahJumpEnv()
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:
print('After ', i, ' steps, done: ', d)
env.reset()
env.close()
alr_envs/alr/mujoco/half_cheetah_jump/mp_wrapper.py
+30
View File
@@ -0,0 +1,30 @@
from typing import Tuple, Union
import numpy as np
from mp_env_api import MPEnvWrapper
class MPWrapper(MPEnvWrapper):
@property
def active_obs(self):
return np.hstack([
[False] * 17,
[True] # goal height
])
@property
def current_pos(self) -> Union[float, int, np.ndarray]:
return self.env.sim.data.qpos[3:9].copy()
@property
def current_vel(self) -> Union[float, int, np.ndarray, Tuple]:
return self.env.sim.data.qvel[3:9].copy()
@property
def goal_pos(self) -> Union[float, int, np.ndarray, Tuple]:
raise ValueError("Goal position is not available and has to be learnt based on the environment.")
@property
def dt(self) -> Union[float, int]:
return self.env.dt