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

added more documentation

Browse Source
This commit is contained in:
ottofabian
2021-08-23 17:24:55 +02:00
parent 45ca0308c1
commit 5c70451018
8 changed files with 419 additions and 450 deletions
Download Patch File Download Diff File Expand all files Collapse all files
alr_envs/__init__.py
+149 -349
View File
@@ -8,6 +8,13 @@ from alr_envs.utils.make_env_helpers import make_detpmp_env
from alr_envs.utils.make_env_helpers import make
from alr_envs.utils.make_env_helpers import make_rank
# Convenience function for all MP environments
ALL_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "DetPMP": []}
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "DetPMP": []}
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "DetPMP": []}
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "DetPMP": []}
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS = {"DMP": [], "DetPMP": []}
# Mujoco
## Reacher
@@ -197,8 +204,9 @@ register(
versions = ["SimpleReacher-v0", "SimpleReacher-v1", "LongSimpleReacher-v0", "LongSimpleReacher-v1"]
for v in versions:
name = v.split("-")
env_id = f'{name[0]}DMP-{name[1]}'
register(
id=f'{name[0]}DMP-{name[1]}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
@@ -215,6 +223,28 @@ for v in versions:
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].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)
register(
id='ViaPointReacherDMP-v0',
@@ -234,6 +264,7 @@ register(
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("ViaPointReacherDMP-v0")
register(
id='ViaPointReacherDetPMP-v0',
@@ -253,12 +284,14 @@ register(
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("ViaPointReacherDetPMP-v0")
## Hole Reacher
versions = ["v0", "v1", "v2"]
for v in versions:
env_id = f'HoleReacherDMP-{v}'
register(
id=f'HoleReacherDMP-{v}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
@@ -277,9 +310,11 @@ for v in versions:
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append(env_id)
env_id = f'HoleReacherDetPMP-{v}'
register(
id=f'HoleReacherDetPMP-{v}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"alr_envs:HoleReacher-{v}",
@@ -295,6 +330,7 @@ for v in versions:
}
}
)
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
## Deep Mind Control Suite (DMC)
### Suite
@@ -305,13 +341,13 @@ register(
# max_episode_steps=1,
kwargs={
"name": f"ball_in_cup-catch",
"time_limit": 2,
"episode_length": 100,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.ball_in_cup.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 2,
"duration": 20,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
@@ -324,19 +360,20 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("dmc_ball_in_cup-catch_dmp-v0")
register(
id=f'dmc_ball_in_cup-catch_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"ball_in_cup-catch",
"time_limit": 2,
"episode_length": 100,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.ball_in_cup.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 2,
"duration": 20,
"width": 0.025,
"policy_type": "motor",
"zero_start": True,
@@ -347,21 +384,21 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("dmc_ball_in_cup-catch_detpmp-v0")
# TODO tune episode length for all below
register(
id=f'dmc_reacher-easy_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"reacher-easy",
"time_limit": 1,
"episode_length": 50,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 1,
"duration": 20,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
@@ -375,19 +412,20 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("dmc_reacher-easy_dmp-v0")
register(
id=f'dmc_reacher-easy_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"reacher-easy",
"time_limit": 1,
"episode_length": 50,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 1,
"duration": 20,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
@@ -399,6 +437,7 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("dmc_reacher-easy_detpmp-v0")
register(
id=f'dmc_reacher-hard_dmp-v0',
@@ -406,13 +445,13 @@ register(
# max_episode_steps=1,
kwargs={
"name": f"reacher-hard",
"time_limit": 1,
"episode_length": 50,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 1,
"duration": 20,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
@@ -426,19 +465,20 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("dmc_reacher-hard_dmp-v0")
register(
id=f'dmc_reacher-hard_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"reacher-hard",
"time_limit": 1,
"episode_length": 50,
"time_limit": 20,
"episode_length": 1000,
"wrappers": [dmc.suite.reacher.MPWrapper],
"mp_kwargs": {
"num_dof": 2,
"num_basis": 5,
"duration": 1,
"duration": 20,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
@@ -450,323 +490,67 @@ register(
}
}
)
register(
id=f'dmc_cartpole-balance_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-balance",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("dmc_reacher-hard_detpmp-v0")
register(
id=f'dmc_cartpole-balance_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-balance",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-balance_sparse_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-balance_sparse",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
dmc_cartpole_tasks = ["balance", "balance_sparse", "swingup", "swingup_sparse", "two_poles", "three_poles"]
register(
id=f'dmc_cartpole-balance_sparse_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-balance_sparse",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
for task in dmc_cartpole_tasks:
env_id = f'dmc_cartpole-{task}_dmp-v0'
register(
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-{task}",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
}
)
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append(env_id)
register(
id=f'dmc_cartpole-swingup_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-swingup",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
env_id = f'dmc_cartpole-{task}_detpmp-v0'
register(
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-{task}",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
}
)
register(
id=f'dmc_cartpole-swingup_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-swingup",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-swingup_sparse_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-swingup_sparse",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-swingup_sparse_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-swingup_sparse",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
"wrappers": [dmc.suite.cartpole.MPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-two_poles_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-two_poles",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
# "wrappers": [partial(DMCCartpoleMPWrapper, n_poles=2)],
"wrappers": [dmc.suite.cartpole.TwoPolesMPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-two_poles_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-two_poles",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
# "wrappers": [partial(DMCCartpoleMPWrapper, n_poles=2)],
"wrappers": [dmc.suite.cartpole.TwoPolesMPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-three_poles_dmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
# max_episode_steps=1,
kwargs={
"name": f"cartpole-three_poles",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
# "wrappers": [partial(DMCCartpoleMPWrapper, n_poles=3)],
"wrappers": [dmc.suite.cartpole.ThreePolesMPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"learn_goal": True,
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
register(
id=f'dmc_cartpole-three_poles_detpmp-v0',
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": f"cartpole-three_poles",
# "time_limit": 1,
"camera_id": 0,
"episode_length": 1000,
# "wrappers": [partial(DMCCartpoleMPWrapper, n_poles=3)],
"wrappers": [dmc.suite.cartpole.ThreePolesMPWrapper],
"mp_kwargs": {
"num_dof": 1,
"num_basis": 5,
"duration": 10,
"width": 0.025,
"policy_type": "motor",
"weights_scale": 0.2,
"zero_start": True,
"policy_kwargs": {
"p_gains": 10,
"d_gains": 10
}
}
}
)
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
### Manipulation
@@ -792,6 +576,7 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("dmc_manipulation-reach_site_dmp-v0")
register(
id=f'dmc_manipulation-reach_site_detpmp-v0',
@@ -812,6 +597,7 @@ register(
}
}
)
ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("dmc_manipulation-reach_site_detpmp-v0")
## Open AI
register(
@@ -835,6 +621,7 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("ContinuousMountainCarDetPMP-v0")
register(
id='ReacherDetPMP-v2',
@@ -857,6 +644,7 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("ReacherDetPMP-v2")
register(
id='FetchSlideDenseDetPMP-v1',
@@ -875,6 +663,7 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("FetchSlideDenseDetPMP-v1")
register(
id='FetchSlideDetPMP-v1',
@@ -893,6 +682,7 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("FetchSlideDetPMP-v1")
register(
id='FetchReachDenseDetPMP-v1',
@@ -911,6 +701,7 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("FetchReachDenseDetPMP-v1")
register(
id='FetchReachDetPMP-v1',
@@ -929,19 +720,21 @@ register(
}
}
)
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append("FetchReachDetPMP-v1")
# MetaWorld
goal_change_envs = ["assembly-v2", "pick-out-of-hole-v2", "plate-slide-v2", "plate-slide-back-v2",
]
for env_id in goal_change_envs:
env_id_split = env_id.split("-")
name = "".join([s.capitalize() for s in env_id_split[:-1]])
for task in goal_change_envs:
task_id_split = task.split("-")
name = "".join([s.capitalize() for s in task_id_split[:-1]])
env_id = f'{name}DetPMP-{task_id_split[-1]}'
register(
id=f'{name}DetPMP-{env_id_split[-1]}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": env_id,
"name": task,
"wrappers": [meta.goal_change.MPWrapper],
"mp_kwargs": {
"num_dof": 4,
@@ -954,13 +747,15 @@ for env_id in goal_change_envs:
}
}
)
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
object_change_envs = ["bin-picking-v2", "hammer-v2", "sweep-into-v2"]
for env_id in object_change_envs:
env_id_split = env_id.split("-")
name = "".join([s.capitalize() for s in env_id_split[:-1]])
for task in object_change_envs:
task_id_split = task.split("-")
name = "".join([s.capitalize() for s in task_id_split[:-1]])
env_id = f'{name}DetPMP-{task_id_split[-1]}'
register(
id=f'{name}DetPMP-{env_id_split[-1]}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": env_id,
@@ -976,6 +771,7 @@ for env_id in object_change_envs:
}
}
)
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
goal_and_object_change_envs = ["box-close-v2", "button-press-v2", "button-press-wall-v2", "button-press-topdown-v2",
"button-press-topdown-wall-v2", "coffee-button-v2", "coffee-pull-v2",
@@ -988,11 +784,12 @@ goal_and_object_change_envs = ["box-close-v2", "button-press-v2", "button-press-
"soccer-v2", "stick-push-v2", "stick-pull-v2", "push-wall-v2", "reach-wall-v2",
"shelf-place-v2", "sweep-v2", "window-open-v2", "window-close-v2"
]
for env_id in goal_and_object_change_envs:
env_id_split = env_id.split("-")
name = "".join([s.capitalize() for s in env_id_split[:-1]])
for task in goal_and_object_change_envs:
task_id_split = task.split("-")
name = "".join([s.capitalize() for s in task_id_split[:-1]])
env_id = f'{name}DetPMP-{task_id_split[-1]}'
register(
id=f'{name}DetPMP-{env_id_split[-1]}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": env_id,
@@ -1008,13 +805,15 @@ for env_id in goal_and_object_change_envs:
}
}
)
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
goal_and_endeffector_change_envs = ["basketball-v2"]
for env_id in goal_and_endeffector_change_envs:
env_id_split = env_id.split("-")
name = "".join([s.capitalize() for s in env_id_split[:-1]])
for task in goal_and_endeffector_change_envs:
task_id_split = task.split("-")
name = "".join([s.capitalize() for s in task_id_split[:-1]])
env_id = f'{name}DetPMP-{task_id_split[-1]}'
register(
id=f'{name}DetPMP-{env_id_split[-1]}',
id=env_id,
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
kwargs={
"name": env_id,
@@ -1030,3 +829,4 @@ for env_id in goal_and_endeffector_change_envs:
}
}
)
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS["DetPMP"].append(env_id)
alr_envs/classic_control/README.MD
+21
View File
@@ -0,0 +1,21 @@
### Classic Control
## Step-based Environments
|Name| Description|Horizon|Action Dimension|Observation Dimension
|---|---|---|---|---|
|`SimpleReacher-v0`| Simple reaching task (2 links) without any physics simulation. Provides no reward until 150 time steps. This allows the agent to explore the space, but requires precise actions towards the end of the trajectory.| 200 | 2 | 9
|`LongSimpleReacher-v0`| Simple reaching task (5 links) without any physics simulation. Provides no reward until 150 time steps. This allows the agent to explore the space, but requires precise actions towards the end of the trajectory.| 200 | 5 | 18
|`ViaPointReacher-v0`| Simple reaching task leveraging a via point, which supports self collision detection. Provides a reward only at 100 and 199 for reaching the viapoint and goal point, respectively.| 200 | 5 | 18
|`HoleReacher-v0`| 5 link reaching task where the end-effector needs to reach into a narrow hole without collding with itself or walls | 200 | 5 | 18
## MP Environments
|Name| Description|Horizon|Action Dimension|Context Dimension
|---|---|---|---|---|
|`ViaPointReacherDMP-v0`| A DMP provides a trajectory for the `ViaPointReacher-v0` task. | 200 | 25
|`HoleReacherFixedGoalDMP-v0`| A DMP provides a trajectory for the `HoleReacher-v0` task with a fixed goal attractor. | 200 | 25
|`HoleReacherDMP-v0`| A DMP provides a trajectory for the `HoleReacher-v0` task. The goal attractor needs to be learned. | 200 | 30
|`ALRBallInACupSimpleDMP-v0`| A DMP provides a trajectory for the `ALRBallInACupSimple-v0` task where only 3 joints are actuated. | 4000 | 15
|`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`|
alr_envs/dmc/README.MD
+17 -1
View File
@@ -1,3 +1,19 @@
# DeepMind Control (DMC) Wrappers
These are the Environment Wrappers for selected [DeepMind Control](https://deepmind.com/research/publications/2020/dm-control-Software-and-Tasks-for-Continuous-Control) environments in order to use our Motion Primitive gym interface with them.
These are the Environment Wrappers for selected
[DeepMind Control](https://deepmind.com/research/publications/2020/dm-control-Software-and-Tasks-for-Continuous-Control)
environments in order to use our Motion Primitive gym interface with them.
## MP Environments
[//]: <> (These environments are wrapped-versions of their Deep Mind Control Suite &#40;DMC&#41; counterparts. Given most task can be)
[//]: <> (solved in shorter horizon lengths than the original 1000 steps, we often shorten the episodes for those task.)
|Name| Description|Trajectory Horizon|Action Dimension|Context Dimension
|---|---|---|---|---|
|`dmc_ball_in_cup-catch_detpmp-v0`| A DetPmP wrapped version of the "catch" task for the "ball_in_cup" environment. | 1000 | 10 | 2
|`dmc_ball_in_cup-catch_dmp-v0`| A DMP wrapped version of the "catch" task for the "ball_in_cup" environment. | 1000| 10 | 2
|`dmc_reacher-easy_detpmp-v0`| A DetPmP wrapped version of the "easy" task for the "reacher" environment. | 1000 | 10 | 4
|`dmc_reacher-easy_dmp-v0`| A DMP wrapped version of the "easy" task for the "reacher" environment. | 1000| 10 | 4
|`dmc_reacher-hard_detpmp-v0`| A DetPmP wrapped version of the "hard" task for the "reacher" environment.| 1000 | 10 | 4
|`dmc_reacher-hard_dmp-v0`| A DMP wrapped version of the "hard" task for the "reacher" environment. | 1000 | 10 | 4
alr_envs/examples/examples_dmc.py
+12 -13
View File
@@ -1,5 +1,4 @@
import alr_envs
from alr_envs.dmc.suite.ball_in_cup.mp_wrapper import MPWrapper
def example_dmc(env_id="fish-swim", seed=1, iterations=1000, render=True):
@@ -62,29 +61,29 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
# Replace this wrapper with the custom wrapper for your environment by inheriting from the MPEnvWrapper.
# You can also add other gym.Wrappers in case they are needed.
wrappers = [MPWrapper]
wrappers = [alr_envs.dmc.suite.ball_in_cup.MPWrapper]
mp_kwargs = {
"num_dof": 2,
"num_basis": 5,
"duration": 20,
"learn_goal": True,
"num_dof": 2, # degrees of fredom a.k.a. the old action space dimensionality
"num_basis": 5, # number of basis functions, the new action space has size num_dof x num_basis
"duration": 20, # length of trajectory in s, number of steps = duration / dt
"learn_goal": True, # learn the goal position (recommended)
"alpha_phase": 2,
"bandwidth_factor": 2,
"policy_type": "motor",
"weights_scale": 50,
"goal_scale": 0.1,
"policy_kwargs": {
"policy_type": "motor", # controller type, 'velocity', 'position', and 'motor' (torque control)
"weights_scale": 1, # scaling of MP weights
"goal_scale": 1, # scaling of learned goal position
"policy_kwargs": { # only required for torque control/PD-Controller
"p_gains": 0.2,
"d_gains": 0.05
}
}
kwargs = {
"time_limit": 20,
"episode_length": 1000,
"time_limit": 20, # same as duration value but as max horizon for underlying DMC environment
"episode_length": 1000, # corresponding number of episode steps
# "frame_skip": 1
}
env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs, **kwargs)
# OR for a deterministic ProMP:
# OR for a deterministic ProMP (other mp_kwargs are required, see metaworld_examples):
# env = alr_envs.make_detpmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_args)
# This renders the full MP trajectory
alr_envs/examples/examples_metaworld.py
+10 -10
View File
@@ -1,5 +1,4 @@
import alr_envs
from alr_envs.meta.goal_and_object_change import MPWrapper
def example_dmc(env_id="fish-swim", seed=1, iterations=1000, render=True):
@@ -65,19 +64,20 @@ def example_custom_dmc_and_mp(seed=1, iterations=1, render=True):
# Replace this wrapper with the custom wrapper for your environment by inheriting from the MPEnvWrapper.
# You can also add other gym.Wrappers in case they are needed.
wrappers = [MPWrapper]
wrappers = [alr_envs.meta.goal_and_object_change.MPWrapper]
mp_kwargs = {
"num_dof": 4,
"num_basis": 5,
"duration": 6.25,
"post_traj_time": 0,
"width": 0.025,
"zero_start": True,
"policy_type": "metaworld",
"num_dof": 4, # degrees of fredom a.k.a. the old action space dimensionality
"num_basis": 5, # number of basis functions, the new action space has size num_dof x num_basis
"duration": 6.25, # length of trajectory in s, number of steps = duration / dt
"post_traj_time": 0, # pad trajectory with additional zeros at the end (recommended: 0)
"width": 0.025, # width of the basis functions
"zero_start": True, # start from current environment position if True
"weights_scale": 1, # scaling of MP weights
"policy_type": "metaworld", # custom controller type for metaworld environments
}
env = alr_envs.make_detpmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs)
# OR for a DMP:
# OR for a DMP (other mp_kwargs are required, see dmc_examples):
# env = alr_envs.make_dmp_env(base_env, wrappers=wrappers, seed=seed, mp_kwargs=mp_kwargs, **kwargs)
# This renders the full MP trajectory
alr_envs/mujoco/README.MD
+15
View File
@@ -0,0 +1,15 @@
# Custom Mujoco tasks
## Step-based Environments
|Name| Description|Horizon|Action Dimension|Observation Dimension
|---|---|---|---|---|
|`ALRReacher-v0`|Modified (5 links) Mujoco gym's `Reacher-v2` (2 links)| 200 | 5 | 21
|`ALRReacherSparse-v0`|Same as `ALRReacher-v0`, but the distance penalty is only provided in the last time step.| 200 | 5 | 21
|`ALRReacherSparseBalanced-v0`|Same as `ALRReacherSparse-v0`, but the end-effector has to remain upright.| 200 | 5 | 21
|`ALRLongReacher-v0`|Modified (7 links) Mujoco gym's `Reacher-v2` (2 links)| 200 | 7 | 27
|`ALRLongReacherSparse-v0`|Same as `ALRLongReacher-v0`, but the distance penalty is only provided in the last time step.| 200 | 7 | 27
|`ALRLongReacherSparseBalanced-v0`|Same as `ALRLongReacherSparse-v0`, but the end-effector has to remain upright.| 200 | 7 | 27
|`ALRBallInACupSimple-v0`| Ball-in-a-cup task where a robot needs to catch a ball attached to a cup at its end-effector. | 4000 | 3 | wip
|`ALRBallInACup-v0`| Ball-in-a-cup task where a robot needs to catch a ball attached to a cup at its end-effector | 4000 | 7 | wip
|`ALRBallInACupGoal-v0`| Similar to `ALRBallInACupSimple-v0` but the ball needs to be caught at a specified goal position | 4000 | 7 | wip
alr_envs/open_ai/README.MD
+12 -1
View File
@@ -1,3 +1,14 @@
# OpenAI Gym Wrappers
These are the Environment Wrappers for selected [OpenAI Gym](https://gym.openai.com/) environments in order to use our Motion Primitive gym interface with them.
These are the Environment Wrappers for selected [OpenAI Gym](https://gym.openai.com/) environments to use
the Motion Primitive gym interface for them.
## MP Environments
These environments are wrapped-versions of their OpenAI-gym counterparts.
|Name| Description|Trajectory Horizon|Action Dimension|Context Dimension
|---|---|---|---|---|
|`ContinuousMountainCarDetPMP-v0`| A DetPmP wrapped version of the ContinuousMountainCar-v0 environment. | 100 | 1
|`ReacherDetPMP-v2`| A DetPmP wrapped version of the Reacher-v2 environment. | 50 | 2
|`FetchSlideDenseDetPMP-v1`| A DetPmP wrapped version of the FetchSlideDense-v1 environment. | 50 | 4
|`FetchReachDenseDetPMP-v1`| A DetPmP wrapped version of the FetchReachDense-v1 environment. | 50 | 4