This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Source: http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/lab1.html | |
import gym | |
import numpy as np | |
from gym.wrappers.monitoring import Monitor | |
from policy import Policy | |
# Task settings: | |
env = gym.make('CartPole-v0') # Change as needed | |
env = Monitor(env, 'tmp/cart-pole-cross-entropy-1', force=True) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from utils import make_policy | |
def do_episode(policy, env, max_steps, render=False): | |
total_rew = 0 | |
ob = env.reset() | |
for t in range(max_steps): | |
a = policy.act(ob) | |
(ob, reward, done, _info) = env.step(a) | |
total_rew += reward |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from utils import make_policy | |
def do_episode(policy, env, max_steps, render=False): | |
total_rew = 0 | |
ob = env.reset() | |
for t in range(max_steps): | |
a = policy.act(ob) | |
(ob, reward, done, _info) = env.step(a) | |
total_rew += reward |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Source: http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/lab1.html | |
import gym | |
import numpy as np | |
from gym.wrappers.monitoring import Monitor | |
from evaluation import noisy_evaluation, do_episode | |
from utils import get_dim_theta, make_policy | |
# Task settings: | |
env = gym.make('CartPole-v0') # Change as needed |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Source: http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/lab1.html | |
import gym | |
import numpy as np | |
from gym.spaces import Discrete, Box | |
from gym.wrappers.monitoring import Monitor | |
# ================================================================ | |
# Policies | |
# ================================================================ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Source: http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/lab1.html | |
import gym | |
import numpy as np | |
from gym.spaces import Discrete, Box | |
from gym.wrappers.monitoring import Monitor | |
# ================================================================ | |
# Policies | |
# ================================================================ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Source: http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/lab1.html | |
import gym | |
import numpy as np | |
from gym.spaces import Discrete, Box | |
from gym.wrappers.monitoring import Monitor | |
# ================================================================ | |
# Policies | |
# ================================================================ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gym | |
import numpy as np | |
from gym.wrappers.monitoring import Monitor | |
MC_POLICY_EVAL_EP = 10 | |
BASE_NOISE_FACTOR = 0.1 | |
NUM_POLICY_EVAL = 500 | |
env = gym.make('CartPole-v0') | |
env = Monitor(env, 'tmp/cart-pole-hill-climb-4', force=True) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gym | |
import numpy as np | |
from gym.wrappers.monitoring import Monitor | |
MC_POLICY_EVAL_EP = 10 | |
BASE_NOISE_FACTOR = 0.5 | |
NUM_POLICY_EVAL = 500 | |
env = gym.make('CartPole-v0') |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gym | |
import numpy as np | |
from gym.wrappers.monitoring import Monitor | |
env = gym.make('CartPole-v0') | |
env = Monitor(env, 'tmp/cart-pole-hill-climb-2', force=True) | |
print("Action space: {0}".format(env.action_space)) | |
print("Observation space: {0}\n\tLow: {1}\n\tHigh: {2}".format( | |
env.observation_space, |
NewerOlder