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

replaced all detpmp with promp

Browse Source
This commit is contained in:
Maximilian Huettenrauch
2021-11-30 16:11:32 +01:00
parent 655d52aa35
commit 8b88ce3476
20 changed files with 121 additions and 407 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alr_envs/alr/__init__.py
+12 -65
View File
@@ -9,7 +9,7 @@ from .mujoco.ball_in_a_cup.biac_pd import ALRBallInACupPDEnv
from .mujoco.reacher.alr_reacher import ALRReacherEnv
from .mujoco.reacher.balancing import BalancingEnv
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "ProMP": [], "DetPMP": []}
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "ProMP": []}
# Classic Control
## Simple Reacher
@@ -213,8 +213,12 @@ for _v in _versions:
"duration": 2,
"alpha_phase": 2,
"learn_goal": True,
"policy_type": "velocity",
"policy_type": "motor",
"weights_scale": 50,
"policy_kwargs": {
"p_gains": .6,
"d_gains": .075
}
}
}
)
@@ -233,33 +237,16 @@ for _v in _versions:
"duration": 2,
"policy_type": "motor",
"weights_scale": 1,
"zero_start": True
"zero_start": True,
"policy_kwargs": {
"p_gains": .6,
"d_gains": .075
}
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["ProMP"].append(_env_id)
_env_id = f'{_name[0]}DetPMP-{_name[1]}'
register(
id=_env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"alr_envs:{_v}",
"wrappers": [classic_control.simple_reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 2 if "long" not in _v.lower() else 5,
"num_basis": 5,
"duration": 2,
"width": 0.025,
"policy_type": "velocity",
"weights_scale": 0.2,
"zero_start": True
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(_env_id)
# Viapoint reacher
register(
id='ViaPointReacherDMP-v0',
@@ -291,7 +278,7 @@ register(
"num_dof": 5,
"num_basis": 5,
"duration": 2,
"policy_type": "motor",
"policy_type": "velocity",
"weights_scale": 1,
"zero_start": True
}
@@ -299,26 +286,6 @@ register(
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["ProMP"].append("ViaPointReacherProMP-v0")
register(
id='ViaPointReacherDetPMP-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": "alr_envs:ViaPointReacher-v0",
"wrappers": [classic_control.viapoint_reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 5,
"num_basis": 5,
"duration": 2,
"width": 0.025,
"policy_type": "velocity",
"weights_scale": 0.2,
"zero_start": True
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("ViaPointReacherDetPMP-v0")
## Hole Reacher
_versions = ["v0", "v1", "v2"]
for _v in _versions:
@@ -363,23 +330,3 @@ for _v in _versions:
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["ProMP"].append(_env_id)
_env_id = f'HoleReacherDetPMP-{_v}'
register(
id=_env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"alr_envs:HoleReacher-{_v}",
"wrappers": [classic_control.hole_reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 5,
"num_basis": 5,
"duration": 2,
"width": 0.025,
"policy_type": "velocity",
"weights_scale": 0.2,
"zero_start": True
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(_env_id)
alr_envs/alr/classic_control/README.MD
+1 -1
View File
@@ -18,4 +18,4 @@
|`ALRBallInACupDMP-v0`| A DMP provides a trajectory for the `ALRBallInACup-v0` task. | 4000 | 35
|`ALRBallInACupGoalDMP-v0`| A DMP provides a trajectory for the `ALRBallInACupGoal-v0` task. | 4000 | 35 | 3
[//]: |`HoleReacherDetPMP-v0`|
[//]: |`HoleReacherProMPP-v0`|
alr_envs/alr/classic_control/viapoint_reacher/viapoint_reacher.py
-1
View File
@@ -5,7 +5,6 @@ import matplotlib.pyplot as plt
import numpy as np
from gym.utils import seeding
from alr_envs.alr.classic_control.utils import check_self_collision
from alr_envs.alr.classic_control.base_reacher.base_reacher_direct import BaseReacherDirectEnv
alr_envs/alr/mujoco/ball_in_a_cup/utils.py
-107
View File
@@ -1,107 +0,0 @@
from alr_envs.alr.mujoco.ball_in_a_cup.ball_in_a_cup import ALRBallInACupEnv
from mp_env_api.mp_wrappers.detpmp_wrapper import DetPMPWrapper
from mp_env_api.mp_wrappers.dmp_wrapper import DmpWrapper
def make_contextual_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBallInACupEnv(reward_type="contextual_goal")
env = DetPMPWrapper(env, num_dof=7, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.5, zero_start=True, zero_goal=True)
env.seed(seed + rank)
return env
return _init
def _make_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBallInACupEnv(reward_type="simple")
env = DetPMPWrapper(env, num_dof=7, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.2, zero_start=True, zero_goal=True)
env.seed(seed + rank)
return env
return _init
def make_simple_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBallInACupEnv(reward_type="simple")
env = DetPMPWrapper(env, num_dof=3, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.25, zero_start=True, zero_goal=True, off=-0.1)
env.seed(seed + rank)
return env
return _init
def make_simple_dmp_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
_env = ALRBallInACupEnv(reward_type="simple")
_env = DmpWrapper(_env,
num_dof=3,
num_basis=5,
duration=3.5,
post_traj_time=4.5,
bandwidth_factor=2.5,
dt=_env.dt,
learn_goal=False,
alpha_phase=3,
start_pos=_env.start_pos[1::2],
final_pos=_env.start_pos[1::2],
policy_type="motor",
weights_scale=100,
)
_env.seed(seed + rank)
return _env
return _init
alr_envs/alr/mujoco/beerpong/utils.py
-72
View File
@@ -1,72 +0,0 @@
from alr_envs.utils.mps.detpmp_wrapper import DetPMPWrapper
from alr_envs.alr.mujoco.beerpong.beerpong import ALRBeerpongEnv
from alr_envs.alr.mujoco.beerpong.beerpong_simple import ALRBeerpongEnv as ALRBeerpongEnvSimple
def make_contextual_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBeerpongEnv()
env = DetPMPWrapper(env, num_dof=7, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.5, zero_start=True, zero_goal=True)
env.seed(seed + rank)
return env
return _init
def _make_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBeerpongEnvSimple()
env = DetPMPWrapper(env, num_dof=7, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.25, zero_start=True, zero_goal=True)
env.seed(seed + rank)
return env
return _init
def make_simple_env(rank, seed=0):
"""
Utility function for multiprocessed env.
:param env_id: (str) the environment ID
:param num_env: (int) the number of environments you wish to have in subprocesses
:param seed: (int) the initial seed for RNG
:param rank: (int) index of the subprocess
:returns a function that generates an environment
"""
def _init():
env = ALRBeerpongEnvSimple()
env = DetPMPWrapper(env, num_dof=3, num_basis=5, width=0.005, duration=3.5, dt=env.dt, post_traj_time=4.5,
policy_type="motor", weights_scale=0.5, zero_start=True, zero_goal=True)
env.seed(seed + rank)
return env
return _init