Python RandomizedEnvWrapper Beispiele

Beispiel #1

Datei: randomized_vecenv.py Projekt: zxxia/active-domainrand

    def _thunk():
        env = gym.make(env_id)
        env = RandomizedEnvWrapper(env, seed + rank)

        env.seed(seed + rank)
        obs_shape = env.observation_space.shape  # TODO: is this something we can remove

        return env

Beispiel #2

#!/usr/bin/env python
import time

import numpy as np
import gym
from tqdm import tqdm

import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

env = gym.make('Pusher3DOFRandomized-v0')
env = RandomizedEnvWrapper(env=env, seed=0)  # env.randomize()

actions = [
    np.array([0.0, 0.0, 1.0]),
    np.array([0.0, 0.0, -1.0]),
    np.array([0.0, 1.0, 0.0]),
    np.array([0.0, -1.0, 0.0]),
    np.array([1.0, 0.0, 0.0]),
    np.array([-1.0, 0.0, 0.0])
]
actions.reverse()

action_change_freq = 50

for env_idx in tqdm(range(10)):
    env.reset()
    env.render()

    for action in actions:

Beispiel #3

# /usr/bin/env python

import time
import gym
import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

env = gym.make('HumanoidRandomizedEnv-v0')
env = RandomizedEnvWrapper(env=env, seed=0)

reward = 0.

env.randomize(randomized_values=[
    "random", "random", "random", "random", "random", "random"
])
env.reset()
env.render()

d = False
while True:
    s_, r, d, info = env.step(env.action_space.sample())
    time.sleep(0.1)

    if d:
        env.randomize(randomized_values=[
            "random", "random", "random", "random", "random", "random"
        ])
        env.reset()
    env.render()

Beispiel #4

Datei: 06-test-randomized-ergoreach.py Projekt: zxxia/active-domainrand

from common.envs.wrappers import RandomizedEnvWrapper

# MODE = "MANUAL" # slow but let's you see what's happening
MODE = "SPEED"  # as fast as possible


def no_op(x):
    pass


if MODE == "MANUAL":
    env = gym.make("ErgoReacherRandomized-Graphical-v0")  # looks nice
    timer = time.sleep
else:
    env = gym.make("ErgoReacherRandomized-Headless-v0")  # runs fast
    timer = no_op

env = RandomizedEnvWrapper(env=env, seed=0)

for _ in tqdm(range(100)):
    env.reset()
    env.randomize(randomized_values=["random"] *
                  8)  # 8 values to randomize over

    while True:
        action = env.action_space.sample()
        obs, rew, done, misc = env.step(action)
        timer(0.05)

        if done:
            break

Beispiel #5

Datei: 08-test-mujoco-4dof-keyboard-control.py Projekt: zxxia/active-domainrand

# manual
"""
This script allows you to manually control the simulator or Duckiebot
using the keyboard arrows.
"""

import sys
from pynput import keyboard
from pynput.keyboard import Key
import numpy as np
import gym
import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

env = gym.make("ErgoReacher4DOFRandomizedHardVisual-v0")
env = RandomizedEnvWrapper(env=env, seed=0)

env.reset()
env.render()

ACTION_KEYS = [
    Key.up, Key.down, Key.page_up, Key.page_down, Key.right, Key.left,
    Key.home, Key.end, Key.alt
]


def on_press(key):
    if key == Key.tab: env.reset()
    if key in ACTION_KEYS:
        action = np.zeros(4)
        if key != Key.alt:

Beispiel #6

import time
from timeit import default_timer as timer
import numpy as np
import tqdm
import gym
import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

np.random.seed(1234)

env = gym.make('PusherRandomized-v0')
env = RandomizedEnvWrapper(env=env, seed=0)

obs = env.reset()

start = timer()
for i in tqdm.tqdm(range(int(1e6))):
    env.randomize(randomized_values=["random", "random", "random"])
print(timer() - start)

Beispiel #7

Datei: 07-test-mujoco-3dof-keyboard-control.py Projekt: zxxia/active-domainrand

# manual
"""
This script allows you to manually control the simulator or Duckiebot
using the keyboard arrows.
"""

import sys
from pynput import keyboard
from pynput.keyboard import Key
import numpy as np
import gym
import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

env = gym.make('Pusher3DOFUberHard-v0')
env = RandomizedEnvWrapper(env=env, seed=0)

reward = 0.

print('hi')
env.randomize(randomized_values=["random", "random"])
env.reset()
env.render()

ACTIONS = [
    np.array([0.0, 0.0, 1.0]),
    np.array([0.0, 0.0, -1.0]),
    np.array([0.0, 1.0, 0.0]),
    np.array([0.0, -1.0, 0.0]),
    np.array([1.0, 0.0, 0.0]),
    np.array([-1.0, 0.0, 0.0])

Beispiel #8

import time
from timeit import default_timer as timer
import numpy as np
import tqdm
import gym
import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

np.random.seed(1234)


env = gym.make('Pusher3DOFRandomized-v0')
env = RandomizedEnvWrapper(env=env, seed=0)

# obs = env.reset()

start = timer()
for i in tqdm.tqdm(range(100)):
    env.randomize(randomized_values=["random", "random", "random"])
    env.reset()
    for _ in range(200):
        obs, reward, done, _ = env.step(env.action_space.sample())
        env.render()
        print(obs)

env.close()
print(timer() - start)

Beispiel #9

#!/usr/bin/env python
import time

import numpy as np
import gym
from tqdm import tqdm

import common.envs
from common.envs.wrappers import RandomizedEnvWrapper

env = gym.make('Pusher3DOFRandomized-v0')
env = RandomizedEnvWrapper(env=env, seed=0)  # env.randomize()

actions = [
    np.array([0.0, 0.0, 1.0]),
    np.array([0.0, 0.0, -1.0]),
    np.array([0.0, 1.0, 0.0]),
    np.array([0.0, -1.0, 0.0]),
    np.array([1.0, 0.0, 0.0]),
    np.array([-1.0, 0.0, 0.0])
]
actions.reverse()

discretization = 50

randomized_values = ["default", "default"]
values = np.linspace(0, 1, discretization)

for dim in range(2):
    for i in tqdm(range(discretization)):
        rands = randomized_values