Merge branch 'master' into reacher_env_cleanup
# Conflicts: # alr_envs/examples/examples_general.py
This commit is contained in:
Maximilian Huettenrauch
+13
-577
@@ -1,579 +1,15 @@
|
||||
import numpy as np
|
||||
from gym.envs.registration import register
|
||||
from alr_envs import dmc, meta, open_ai
|
||||
from alr_envs.utils.make_env_helpers import make, make_detpmp_env, make_dmp_env, make_rank
|
||||
from alr_envs.utils import make_dmc
|
||||
|
||||
from alr_envs.classic_control.hole_reacher.hole_reacher_mp_wrapper import HoleReacherMPWrapper
|
||||
from alr_envs.classic_control.simple_reacher.simple_reacher_mp_wrapper import SimpleReacherMPWrapper
|
||||
from alr_envs.classic_control.viapoint_reacher.viapoint_reacher_mp_wrapper import ViaPointReacherMPWrapper
|
||||
from alr_envs.dmc.ball_in_cup.ball_in_the_cup_mp_wrapper import DMCBallInCupMPWrapper
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup_mp_wrapper import BallInACupMPWrapper
|
||||
from alr_envs.stochastic_search.functions.f_rosenbrock import Rosenbrock
|
||||
# Convenience function for all MP environments
|
||||
from .alr import ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS
|
||||
from .dmc import ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS
|
||||
from .meta import ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS
|
||||
from .open_ai import ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS
|
||||
|
||||
# Mujoco
|
||||
|
||||
## Reacher
|
||||
register(
|
||||
id='ALRReacher-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 0,
|
||||
"n_links": 5,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRReacherSparse-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 5,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRReacherSparseBalanced-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 5,
|
||||
"balance": True,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacher-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 0,
|
||||
"n_links": 7,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacherSparse-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 7,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacherSparseBalanced-v0',
|
||||
entry_point='alr_envs.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 7,
|
||||
"balance": True,
|
||||
}
|
||||
)
|
||||
|
||||
## Balancing Reacher
|
||||
|
||||
register(
|
||||
id='Balancing-v0',
|
||||
entry_point='alr_envs.mujoco:BalancingEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupSimple-v0',
|
||||
entry_point='alr_envs.mujoco:ALRBallInACupEnv',
|
||||
max_episode_steps=4000,
|
||||
kwargs={
|
||||
"simplified": True,
|
||||
"reward_type": "no_context",
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupPDSimple-v0',
|
||||
entry_point='alr_envs.mujoco:ALRBallInACupPDEnv',
|
||||
max_episode_steps=4000,
|
||||
kwargs={
|
||||
"simplified": True,
|
||||
"reward_type": "no_context"
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupPD-v0',
|
||||
entry_point='alr_envs.mujoco:ALRBallInACupPDEnv',
|
||||
max_episode_steps=4000,
|
||||
kwargs={
|
||||
"simplified": False,
|
||||
"reward_type": "no_context"
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACup-v0',
|
||||
entry_point='alr_envs.mujoco:ALRBallInACupEnv',
|
||||
max_episode_steps=4000,
|
||||
kwargs={
|
||||
"reward_type": "no_context"
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupGoal-v0',
|
||||
entry_point='alr_envs.mujoco:ALRBallInACupEnv',
|
||||
max_episode_steps=4000,
|
||||
kwargs={
|
||||
"reward_type": "contextual_goal"
|
||||
}
|
||||
)
|
||||
|
||||
# Classic control
|
||||
|
||||
## Simple Reacher
|
||||
register(
|
||||
id='SimpleReacher-v0',
|
||||
entry_point='alr_envs.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 2,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='SimpleReacher-v1',
|
||||
entry_point='alr_envs.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 2,
|
||||
"random_start": False
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='LongSimpleReacher-v0',
|
||||
entry_point='alr_envs.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='LongSimpleReacher-v1',
|
||||
entry_point='alr_envs.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False
|
||||
}
|
||||
)
|
||||
|
||||
## Viapoint Reacher
|
||||
|
||||
register(
|
||||
id='ViaPointReacher-v0',
|
||||
entry_point='alr_envs.classic_control:ViaPointReacher',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"allow_self_collision": False,
|
||||
"collision_penalty": 1000
|
||||
}
|
||||
)
|
||||
|
||||
## Hole Reacher
|
||||
register(
|
||||
id='HoleReacher-v0',
|
||||
entry_point='alr_envs.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": True,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": None,
|
||||
"hole_depth": 1,
|
||||
"hole_x": None,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='HoleReacher-v1',
|
||||
entry_point='alr_envs.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": None,
|
||||
"hole_depth": 1,
|
||||
"hole_x": None,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='HoleReacher-v2',
|
||||
entry_point='alr_envs.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": 0.25,
|
||||
"hole_depth": 1,
|
||||
"hole_x": 2,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
# MP environments
|
||||
|
||||
## Simple Reacher
|
||||
versions = ["SimpleReacher-v0", "SimpleReacher-v1", "LongSimpleReacher-v0", "LongSimpleReacher-v1"]
|
||||
for v in versions:
|
||||
name = v.split("-")
|
||||
register(
|
||||
id=f'{name[0]}DMP-{name[1]}',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": f"alr_envs:{v}",
|
||||
"wrappers": [SimpleReacherMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 2 if "long" not in v.lower() else 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"alpha_phase": 2,
|
||||
"learn_goal": True,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ViaPointReacherDMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": "alr_envs:ViaPointReacher-v0",
|
||||
"wrappers": [ViaPointReacherMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 2,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
## Hole Reacher
|
||||
versions = ["v0", "v1", "v2"]
|
||||
for v in versions:
|
||||
register(
|
||||
id=f'HoleReacherDMP-{v}',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": f"alr_envs:HoleReacher-{v}",
|
||||
"wrappers": [HoleReacherMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 2,
|
||||
"bandwidth_factor": 2,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
"goal_scale": 0.1
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id=f'HoleReacherDetPMP-{v}',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
|
||||
kwargs={
|
||||
"name": f"alr_envs:HoleReacher-{v}",
|
||||
"wrappers": [HoleReacherMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"width": 0.025,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
# TODO: properly add final_pos
|
||||
register(
|
||||
id='HoleReacherFixedGoalDMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": "alr_envs:HoleReacher-v0",
|
||||
"wrappers": [HoleReacherMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"learn_goal": False,
|
||||
"alpha_phase": 2,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
"goal_scale": 0.1
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
## Ball in Cup
|
||||
|
||||
register(
|
||||
id='ALRBallInACupSimpleDMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupSimple-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 3,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"learn_goal": False,
|
||||
"alpha_phase": 3,
|
||||
"bandwidth_factor": 2.5,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 100,
|
||||
"return_to_start": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupDMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACup-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 7,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"learn_goal": False,
|
||||
"alpha_phase": 3,
|
||||
"bandwidth_factor": 2.5,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 100,
|
||||
"return_to_start": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupSimpleDetPMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupSimple-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 3,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"width": 0.0035,
|
||||
# "off": -0.05,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True,
|
||||
"zero_goal": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupPDSimpleDetPMP-v0',
|
||||
entry_point='alr_envs.mujoco.ball_in_a_cup.biac_pd:make_detpmp_env_helper',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupPDSimple-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 3,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"width": 0.0035,
|
||||
# "off": -0.05,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True,
|
||||
"zero_goal": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupPDDetPMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupPD-v0",
|
||||
"num_dof": 7,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"width": 0.0035,
|
||||
# "off": -0.05,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True,
|
||||
"zero_goal": True,
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupDetPMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_detpmp_env_helper',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupSimple-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 7,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"width": 0.0035,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True,
|
||||
"zero_goal": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRBallInACupGoalDMP-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_contextual_env',
|
||||
kwargs={
|
||||
"name": "alr_envs:ALRBallInACupGoal-v0",
|
||||
"wrappers": [BallInACupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 7,
|
||||
"num_basis": 5,
|
||||
"duration": 3.5,
|
||||
"post_traj_time": 4.5,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 3,
|
||||
"bandwidth_factor": 2.5,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 50,
|
||||
"goal_scale": 0.1,
|
||||
"policy_kwargs": {
|
||||
"p_gains": np.array([4. / 3., 2.4, 2.5, 5. / 3., 2., 2., 1.25]),
|
||||
"d_gains": np.array([0.0466, 0.12, 0.125, 0.04166, 0.06, 0.06, 0.025])
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
## DMC
|
||||
|
||||
register(
|
||||
id=f'dmc_ball_in_cup-catch_dmp-v0',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": f"ball_in_cup-catch",
|
||||
"wrappers": [DMCBallInCupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 2,
|
||||
"num_basis": 5,
|
||||
"duration": 20,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 2,
|
||||
"bandwidth_factor": 2,
|
||||
"policy_type": "motor",
|
||||
"weights_scale": 50,
|
||||
"goal_scale": 0.1,
|
||||
"policy_kwargs": {
|
||||
"p_gains": 0.2,
|
||||
"d_gains": 0.05
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
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",
|
||||
"wrappers": [DMCBallInCupMPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 2,
|
||||
"num_basis": 5,
|
||||
"duration": 20,
|
||||
"width": 0.025,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 0.2,
|
||||
"zero_start": True,
|
||||
"policy_kwargs": {
|
||||
"p_gains": 0.2,
|
||||
"d_gains": 0.05
|
||||
}
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
# BBO functions
|
||||
|
||||
for dim in [5, 10, 25, 50, 100]:
|
||||
register(
|
||||
id=f'Rosenbrock{dim}-v0',
|
||||
entry_point='alr_envs.stochastic_search:StochasticSearchEnv',
|
||||
max_episode_steps=1,
|
||||
kwargs={
|
||||
"cost_f": Rosenbrock(dim),
|
||||
}
|
||||
)
|
||||
ALL_MOTION_PRIMITIVE_ENVIRONMENTS = {
|
||||
key: value + ALL_DEEPMIND_MOTION_PRIMITIVE_ENVIRONMENTS[key] +
|
||||
ALL_GYM_MOTION_PRIMITIVE_ENVIRONMENTS[key] +
|
||||
ALL_METAWORLD_MOTION_PRIMITIVE_ENVIRONMENTS[key]
|
||||
for key, value in ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS.items()}
|
||||
|
||||
@@ -0,0 +1,329 @@
|
||||
from gym import register
|
||||
|
||||
from . import classic_control, mujoco
|
||||
from .classic_control.hole_reacher.hole_reacher import HoleReacherEnv
|
||||
from .classic_control.simple_reacher.simple_reacher import SimpleReacherEnv
|
||||
from .classic_control.viapoint_reacher.viapoint_reacher import ViaPointReacherEnv
|
||||
from .mujoco.ball_in_a_cup.ball_in_a_cup import ALRBallInACupEnv
|
||||
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": [], "DetPMP": []}
|
||||
|
||||
# Classic Control
|
||||
## Simple Reacher
|
||||
register(
|
||||
id='SimpleReacher-v0',
|
||||
entry_point='alr_envs.alr.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 2,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='SimpleReacher-v1',
|
||||
entry_point='alr_envs.alr.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 2,
|
||||
"random_start": False
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='LongSimpleReacher-v0',
|
||||
entry_point='alr_envs.alr.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='LongSimpleReacher-v1',
|
||||
entry_point='alr_envs.alr.classic_control:SimpleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False
|
||||
}
|
||||
)
|
||||
|
||||
## Viapoint Reacher
|
||||
|
||||
register(
|
||||
id='ViaPointReacher-v0',
|
||||
entry_point='alr_envs.alr.classic_control:ViaPointReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"allow_self_collision": False,
|
||||
"collision_penalty": 1000
|
||||
}
|
||||
)
|
||||
|
||||
## Hole Reacher
|
||||
register(
|
||||
id='HoleReacher-v0',
|
||||
entry_point='alr_envs.alr.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": True,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": None,
|
||||
"hole_depth": 1,
|
||||
"hole_x": None,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='HoleReacher-v1',
|
||||
entry_point='alr_envs.alr.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": 0.25,
|
||||
"hole_depth": 1,
|
||||
"hole_x": None,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='HoleReacher-v2',
|
||||
entry_point='alr_envs.alr.classic_control:HoleReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
"random_start": False,
|
||||
"allow_self_collision": False,
|
||||
"allow_wall_collision": False,
|
||||
"hole_width": 0.25,
|
||||
"hole_depth": 1,
|
||||
"hole_x": 2,
|
||||
"collision_penalty": 100,
|
||||
}
|
||||
)
|
||||
|
||||
# Mujoco
|
||||
|
||||
## Reacher
|
||||
register(
|
||||
id='ALRReacher-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 0,
|
||||
"n_links": 5,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRReacherSparse-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 5,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRReacherSparseBalanced-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 5,
|
||||
"balance": True,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacher-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 0,
|
||||
"n_links": 7,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacherSparse-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 7,
|
||||
"balance": False,
|
||||
}
|
||||
)
|
||||
|
||||
register(
|
||||
id='ALRLongReacherSparseBalanced-v0',
|
||||
entry_point='alr_envs.alr.mujoco:ALRReacherEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"steps_before_reward": 200,
|
||||
"n_links": 7,
|
||||
"balance": True,
|
||||
}
|
||||
)
|
||||
|
||||
## Balancing Reacher
|
||||
|
||||
register(
|
||||
id='Balancing-v0',
|
||||
entry_point='alr_envs.alr.mujoco:BalancingEnv',
|
||||
max_episode_steps=200,
|
||||
kwargs={
|
||||
"n_links": 5,
|
||||
}
|
||||
)
|
||||
|
||||
# Motion Primitive Environments
|
||||
|
||||
## Simple Reacher
|
||||
_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=_env_id,
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_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": 20,
|
||||
"alpha_phase": 2,
|
||||
"learn_goal": True,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
}
|
||||
}
|
||||
)
|
||||
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": 20,
|
||||
"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',
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_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,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 2,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
}
|
||||
}
|
||||
)
|
||||
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].append("ViaPointReacherDMP-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:
|
||||
_env_id = f'HoleReacherDMP-{_v}'
|
||||
register(
|
||||
id=_env_id,
|
||||
entry_point='alr_envs.utils.make_env_helpers:make_dmp_env_helper',
|
||||
# max_episode_steps=1,
|
||||
kwargs={
|
||||
"name": f"alr_envs:HoleReacher-{_v}",
|
||||
"wrappers": [classic_control.hole_reacher.MPWrapper],
|
||||
"mp_kwargs": {
|
||||
"num_dof": 5,
|
||||
"num_basis": 5,
|
||||
"duration": 2,
|
||||
"learn_goal": True,
|
||||
"alpha_phase": 2,
|
||||
"bandwidth_factor": 2,
|
||||
"policy_type": "velocity",
|
||||
"weights_scale": 50,
|
||||
"goal_scale": 0.1
|
||||
}
|
||||
}
|
||||
)
|
||||
ALL_ALR_MOTION_PRIMITIVE_ENVIRONMENTS["DMP"].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)
|
||||
@@ -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`|
|
||||
@@ -0,0 +1,3 @@
|
||||
from .hole_reacher.hole_reacher import HoleReacherEnv
|
||||
from .simple_reacher.simple_reacher import SimpleReacherEnv
|
||||
from .viapoint_reacher.viapoint_reacher import ViaPointReacherEnv
|
||||
@@ -0,0 +1 @@
|
||||
from .mp_wrapper import MPWrapper
|
||||
+22
-9
@@ -6,7 +6,7 @@ import numpy as np
|
||||
from gym.utils import seeding
|
||||
from matplotlib import patches
|
||||
|
||||
from alr_envs.classic_control.utils import check_self_collision
|
||||
from alr_envs.alr.classic_control.utils import check_self_collision
|
||||
|
||||
|
||||
class HoleReacherEnv(gym.Env):
|
||||
@@ -122,12 +122,26 @@ class HoleReacherEnv(gym.Env):
|
||||
return self._get_obs().copy()
|
||||
|
||||
def _generate_hole(self):
|
||||
self._tmp_x = self.np_random.uniform(1, 3.5, 1) if self.initial_x is None else np.copy(self.initial_x)
|
||||
self._tmp_width = self.np_random.uniform(0.15, 0.5, 1) if self.initial_width is None else np.copy(
|
||||
self.initial_width)
|
||||
# TODO we do not want this right now.
|
||||
self._tmp_depth = self.np_random.uniform(1, 1, 1) if self.initial_depth is None else np.copy(
|
||||
self.initial_depth)
|
||||
if self.initial_width is None:
|
||||
width = self.np_random.uniform(0.15, 0.5)
|
||||
else:
|
||||
width = np.copy(self.initial_width)
|
||||
if self.initial_x is None:
|
||||
# sample whole on left or right side
|
||||
direction = self.np_random.choice([-1, 1])
|
||||
# Hole center needs to be half the width away from the arm to give a valid setting.
|
||||
x = direction * self.np_random.uniform(width / 2, 3.5)
|
||||
else:
|
||||
x = np.copy(self.initial_x)
|
||||
if self.initial_depth is None:
|
||||
# TODO we do not want this right now.
|
||||
depth = self.np_random.uniform(1, 1)
|
||||
else:
|
||||
depth = np.copy(self.initial_depth)
|
||||
|
||||
self._tmp_width = width
|
||||
self._tmp_x = x
|
||||
self._tmp_depth = depth
|
||||
self._goal = np.hstack([self._tmp_x, -self._tmp_depth])
|
||||
|
||||
def _update_joints(self):
|
||||
@@ -202,7 +216,6 @@ class HoleReacherEnv(gym.Env):
|
||||
return np.squeeze(end_effector + self._joints[0, :])
|
||||
|
||||
def _check_wall_collision(self, line_points):
|
||||
|
||||
# all points that are before the hole in x
|
||||
r, c = np.where(line_points[:, :, 0] < (self._tmp_x - self._tmp_width / 2))
|
||||
|
||||
@@ -250,7 +263,7 @@ class HoleReacherEnv(gym.Env):
|
||||
self.fig.show()
|
||||
|
||||
self.fig.gca().set_title(
|
||||
f"Iteration: {self._steps}, distance: {self.end_effector - self._goal}")
|
||||
f"Iteration: {self._steps}, distance: {np.linalg.norm(self.end_effector - self._goal) ** 2}")
|
||||
|
||||
if mode == "human":
|
||||
|
||||
+2
-2
@@ -2,10 +2,10 @@ from typing import Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
|
||||
from mp_env_api import MPEnvWrapper
|
||||
|
||||
|
||||
class HoleReacherMPWrapper(MPEnvWrapper):
|
||||
class MPWrapper(MPEnvWrapper):
|
||||
@property
|
||||
def active_obs(self):
|
||||
return np.hstack([
|
||||
@@ -0,0 +1 @@
|
||||
from .mp_wrapper import MPWrapper
|
||||
+2
-2
@@ -2,10 +2,10 @@ from typing import Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
|
||||
from mp_env_api import MPEnvWrapper
|
||||
|
||||
|
||||
class SimpleReacherMPWrapper(MPEnvWrapper):
|
||||
class MPWrapper(MPEnvWrapper):
|
||||
@property
|
||||
def active_obs(self):
|
||||
return np.hstack([
|
||||
@@ -0,0 +1 @@
|
||||
from .mp_wrapper import MPWrapper
|
||||
+2
-2
@@ -2,10 +2,10 @@ from typing import Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
|
||||
from mp_env_api import MPEnvWrapper
|
||||
|
||||
|
||||
class ViaPointReacherMPWrapper(MPEnvWrapper):
|
||||
class MPWrapper(MPEnvWrapper):
|
||||
@property
|
||||
def active_obs(self):
|
||||
return np.hstack([
|
||||
+2
-2
@@ -5,10 +5,10 @@ import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
from gym.utils import seeding
|
||||
|
||||
from alr_envs.classic_control.utils import check_self_collision
|
||||
from alr_envs.alr.classic_control.utils import check_self_collision
|
||||
|
||||
|
||||
class ViaPointReacher(gym.Env):
|
||||
class ViaPointReacherEnv(gym.Env):
|
||||
|
||||
def __init__(self, n_links, random_start: bool = False, via_target: Union[None, Iterable] = None,
|
||||
target: Union[None, Iterable] = None, allow_self_collision=False, collision_penalty=1000):
|
||||
@@ -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
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
from .reacher.alr_reacher import ALRReacherEnv
|
||||
from .reacher.balancing import BalancingEnv
|
||||
from .ball_in_a_cup.ball_in_a_cup import ALRBallInACupEnv
|
||||
from .ball_in_a_cup.biac_pd import ALRBallInACupPDEnv
|
||||
+2
-2
@@ -35,10 +35,10 @@ class ALRBallInACupEnv(MujocoEnv, utils.EzPickle):
|
||||
self.sim_time = 8 # seconds
|
||||
self.sim_steps = int(self.sim_time / self.dt)
|
||||
if reward_type == "no_context":
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup_reward_simple import BallInACupReward
|
||||
from alr_envs.alr.mujoco.ball_in_a_cup.ball_in_a_cup_reward_simple import BallInACupReward
|
||||
reward_function = BallInACupReward
|
||||
elif reward_type == "contextual_goal":
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup_reward import BallInACupReward
|
||||
from alr_envs.alr.mujoco.ball_in_a_cup.ball_in_a_cup_reward import BallInACupReward
|
||||
reward_function = BallInACupReward
|
||||
else:
|
||||
raise ValueError("Unknown reward type: {}".format(reward_type))
|
||||
+1
-1
@@ -2,7 +2,7 @@ from typing import Tuple, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
from mp_env_api.interface_wrappers.mp_env_wrapper import MPEnvWrapper
|
||||
from mp_env_api import MPEnvWrapper
|
||||
|
||||
|
||||
class BallInACupMPWrapper(MPEnvWrapper):
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
import numpy as np
|
||||
from alr_envs.mujoco import alr_reward_fct
|
||||
from alr_envs.alr.mujoco import alr_reward_fct
|
||||
|
||||
|
||||
class BallInACupReward(alr_reward_fct.AlrReward):
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
import numpy as np
|
||||
from alr_envs.mujoco import alr_reward_fct
|
||||
from alr_envs.alr.mujoco import alr_reward_fct
|
||||
|
||||
|
||||
class BallInACupReward(alr_reward_fct.AlrReward):
|
||||
+2
-2
@@ -42,10 +42,10 @@ class ALRBallInACupPDEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
||||
self._dt = 0.02
|
||||
self.ep_length = 4000 # based on 8 seconds with dt = 0.02 int(self.sim_time / self.dt)
|
||||
if reward_type == "no_context":
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup_reward_simple import BallInACupReward
|
||||
from alr_envs.alr.mujoco.ball_in_a_cup.ball_in_a_cup_reward_simple import BallInACupReward
|
||||
reward_function = BallInACupReward
|
||||
elif reward_type == "contextual_goal":
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup_reward import BallInACupReward
|
||||
from alr_envs.alr.mujoco.ball_in_a_cup.ball_in_a_cup_reward import BallInACupReward
|
||||
reward_function = BallInACupReward
|
||||
else:
|
||||
raise ValueError("Unknown reward type: {}".format(reward_type))
|
||||
@@ -1,4 +1,4 @@
|
||||
from alr_envs.mujoco.ball_in_a_cup.ball_in_a_cup import ALRBallInACupEnv
|
||||
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
|
||||
|
||||
@@ -37,7 +37,7 @@ class ALRBeerpongEnv(MujocoEnv, utils.EzPickle):
|
||||
self.sim_time = 8 # seconds
|
||||
self.sim_steps = int(self.sim_time / self.dt)
|
||||
if reward_function is None:
|
||||
from alr_envs.mujoco.beerpong.beerpong_reward import BeerpongReward
|
||||
from alr_envs.alr.mujoco.beerpong.beerpong_reward import BeerpongReward
|
||||
reward_function = BeerpongReward
|
||||
self.reward_function = reward_function(self.sim, self.sim_steps)
|
||||
self.cup_robot_id = self.sim.model._site_name2id["cup_robot_final"]
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
import numpy as np
|
||||
from alr_envs.mujoco import alr_reward_fct
|
||||
from alr_envs.alr.mujoco import alr_reward_fct
|
||||
|
||||
|
||||
class BeerpongReward(alr_reward_fct.AlrReward):
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
import numpy as np
|
||||
from alr_envs.mujoco import alr_reward_fct
|
||||
from alr_envs.alr.mujoco import alr_reward_fct
|
||||
|
||||
|
||||
class BeerpongReward(alr_reward_fct.AlrReward):
|
||||
+1
-1
@@ -38,7 +38,7 @@ class ALRBeerpongEnv(MujocoEnv, utils.EzPickle):
|
||||
self.sim_time = 8 # seconds
|
||||
self.sim_steps = int(self.sim_time / self.dt)
|
||||
if reward_function is None:
|
||||
from alr_envs.mujoco.beerpong.beerpong_reward_simple import BeerpongReward
|
||||
from alr_envs.alr.mujoco.beerpong.beerpong_reward_simple import BeerpongReward
|
||||
reward_function = BeerpongReward
|
||||
self.reward_function = reward_function(self.sim, self.sim_steps)
|
||||
self.cup_robot_id = self.sim.model._site_name2id["cup_robot_final"]
|
||||
@@ -1,6 +1,6 @@
|
||||
from alr_envs.utils.mps.detpmp_wrapper import DetPMPWrapper
|
||||
from alr_envs.mujoco.beerpong.beerpong import ALRBeerpongEnv
|
||||
from alr_envs.mujoco.beerpong.beerpong_simple import ALRBeerpongEnv as ALRBeerpongEnvSimple
|
||||
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):
|
||||
+2
-2
@@ -2,9 +2,9 @@ import numpy as np
|
||||
from gym import spaces
|
||||
from gym.envs.robotics import robot_env, utils
|
||||
# import xml.etree.ElementTree as ET
|
||||
from alr_envs.mujoco.gym_table_tennis.utils.rewards.hierarchical_reward import HierarchicalRewardTableTennis
|
||||
from alr_envs.alr.mujoco.gym_table_tennis.utils.rewards.hierarchical_reward import HierarchicalRewardTableTennis
|
||||
import glfw
|
||||
from alr_envs.mujoco.gym_table_tennis.utils.experiment import ball_initialize
|
||||
from alr_envs.alr.mujoco.gym_table_tennis.utils.experiment import ball_initialize
|
||||
from pathlib import Path
|
||||
import os
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
import numpy as np
|
||||
from gym.utils import seeding
|
||||
from alr_envs.mujoco.gym_table_tennis.utils.util import read_yaml, read_json
|
||||
from alr_envs.alr.mujoco.gym_table_tennis.utils.util import read_yaml, read_json
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user