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/walker_2d_jump/__init__.py
+1
View File
@@ -0,0 +1 @@
from .mp_wrapper import MPWrapper
alr_envs/alr/mujoco/walker_2d_jump/assets/walker2d.xml
+62
View File
@@ -0,0 +1,62 @@
<mujoco model="walker2d">
<compiler angle="degree" coordinate="global" inertiafromgeom="true"/>
<default>
<joint armature="0.01" damping=".1" limited="true"/>
<geom conaffinity="0" condim="3" contype="1" density="1000" friction=".7 .1 .1" rgba="0.8 0.6 .4 1"/>
</default>
<option integrator="RK4" timestep="0.002"/>
<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" name="floor" pos="0 0 0" rgba="0.8 0.9 0.8 1" size="40 40 40" type="plane" material="MatPlane"/>
<body name="torso" pos="0 0 1.25">
<camera name="track" mode="trackcom" pos="0 -3 1" 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" ref="1.25" stiffness="0" type="slide"/>
<joint armature="0" axis="0 1 0" damping="0" limited="false" name="rooty" pos="0 0 1.25" stiffness="0" type="hinge"/>
<geom friction="0.9" fromto="0 0 1.45 0 0 1.05" name="torso_geom" size="0.05" type="capsule"/>
<body name="thigh" pos="0 0 1.05">
<joint axis="0 -1 0" name="thigh_joint" pos="0 0 1.05" range="-150 0" type="hinge"/>
<geom friction="0.9" fromto="0 0 1.05 0 0 0.6" name="thigh_geom" size="0.05" type="capsule"/>
<body name="leg" pos="0 0 0.35">
<joint axis="0 -1 0" name="leg_joint" pos="0 0 0.6" range="-150 0" type="hinge"/>
<geom friction="0.9" fromto="0 0 0.6 0 0 0.1" name="leg_geom" size="0.04" type="capsule"/>
<body name="foot" pos="0.2/2 0 0.1">
<joint axis="0 -1 0" name="foot_joint" pos="0 0 0.1" range="-45 45" type="hinge"/>
<geom friction="0.9" fromto="-0.0 0 0.1 0.2 0 0.1" name="foot_geom" size="0.06" type="capsule"/>
</body>
</body>
</body>
<!-- copied and then replace thigh->thigh_left, leg->leg_left, foot->foot_right -->
<body name="thigh_left" pos="0 0 1.05">
<joint axis="0 -1 0" name="thigh_left_joint" pos="0 0 1.05" range="-150 0" type="hinge"/>
<geom friction="0.9" fromto="0 0 1.05 0 0 0.6" name="thigh_left_geom" rgba=".7 .3 .6 1" size="0.05" type="capsule"/>
<body name="leg_left" pos="0 0 0.35">
<joint axis="0 -1 0" name="leg_left_joint" pos="0 0 0.6" range="-150 0" type="hinge"/>
<geom friction="0.9" fromto="0 0 0.6 0 0 0.1" name="leg_left_geom" rgba=".7 .3 .6 1" size="0.04" type="capsule"/>
<body name="foot_left" pos="0.2/2 0 0.1">
<joint axis="0 -1 0" name="foot_left_joint" pos="0 0 0.1" range="-45 45" type="hinge"/>
<geom friction="1.9" fromto="-0.0 0 0.1 0.2 0 0.1" name="foot_left_geom" rgba=".7 .3 .6 1" size="0.06" type="capsule"/>
</body>
</body>
</body>
</body>
</worldbody>
<actuator>
<!-- <motor joint="torso_joint" ctrlrange="-100.0 100.0" isctrllimited="true"/>-->
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="thigh_joint"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="leg_joint"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="foot_joint"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="thigh_left_joint"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="leg_left_joint"/>
<motor ctrllimited="true" ctrlrange="-1.0 1.0" gear="100" joint="foot_left_joint"/>
<!-- <motor joint="finger2_rot" ctrlrange="-20.0 20.0" isctrllimited="true"/>-->
</actuator>
<asset>
<texture type="skybox" builtin="gradient" rgb1=".4 .5 .6" rgb2="0 0 0"
width="100" height="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>
</mujoco>
alr_envs/alr/mujoco/walker_2d_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 pos
])
@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
alr_envs/alr/mujoco/walker_2d_jump/walker_2d_jump.py
+113
View File
@@ -0,0 +1,113 @@
import os
from gym.envs.mujoco.walker2d_v3 import Walker2dEnv
import numpy as np
MAX_EPISODE_STEPS_WALKERJUMP = 300
class ALRWalker2dJumpEnv(Walker2dEnv):
"""
healthy reward 1.0 -> 0.005 -> 0.0025 not from alex
penalty 10 -> 0 not from alex
"""
def __init__(self,
xml_file='walker2d.xml',
forward_reward_weight=1.0,
ctrl_cost_weight=1e-3,
healthy_reward=0.0025,
terminate_when_unhealthy=True,
healthy_z_range=(0.8, 2.0),
healthy_angle_range=(-1.0, 1.0),
reset_noise_scale=5e-3,
penalty=0,
context=True,
exclude_current_positions_from_observation=True,
max_episode_steps=300):
self.current_step = 0
self.max_episode_steps = max_episode_steps
self.max_height = 0
self._penalty = penalty
self.context = context
self.goal = 0
xml_file = os.path.join(os.path.dirname(__file__), "assets", xml_file)
super().__init__(xml_file, forward_reward_weight, ctrl_cost_weight, healthy_reward, terminate_when_unhealthy,
healthy_z_range, healthy_angle_range, reset_noise_scale,
exclude_current_positions_from_observation)
def step(self, action):
self.current_step += 1
self.do_simulation(action, self.frame_skip)
#pos_after = self.get_body_com("torso")[0]
height = self.get_body_com("torso")[2]
self.max_height = max(height, self.max_height)
fell_over = height < 0.2
done = fell_over
ctrl_cost = self.control_cost(action)
costs = ctrl_cost
if self.current_step >= self.max_episode_steps or done:
done = True
height_goal_distance = -10 * (np.linalg.norm(self.max_height - self.goal)) if self.context else self.max_height
healthy_reward = self.healthy_reward * self.current_step
rewards = height_goal_distance + healthy_reward
else:
# penalty not needed
rewards = 0
rewards += ((action[:2] > 0) * self._penalty).sum() if self.current_step < 4 else 0
rewards += ((action[3:5] > 0) * self._penalty).sum() if self.current_step < 4 else 0
observation = self._get_obs()
reward = rewards - costs
info = {
'height': height,
'max_height': self.max_height,
'goal' : self.goal,
}
return observation, reward, done, info
def _get_obs(self):
return np.append(super()._get_obs(), self.goal)
def reset(self):
self.current_step = 0
self.max_height = 0
self.goal = np.random.uniform(1.5, 2.5, 1) # 1.5 3.0
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 = ALRWalker2dJumpEnv()
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()