malzantot

"""
Q-Learning example using OpenAI gym MountainCar enviornment

Author: Moustafa Alzantot (malzantot@ucla.edu)

"""
import numpy as np

import gym
from gym import wrappers

malzantot

"""
Solving FrozenLake8x8 environment using Policy iteration.
Author : Moustafa Alzantot (malzantot@ucla.edu)
"""
import numpy as np
import gym
from gym import wrappers


def run_episode(env, policy, gamma = 1.0, render = False):

malzantot

"""
Solving FrozenLake8x8 environment using Value-Itertion.


Author : Moustafa Alzantot (malzantot@ucla.edu)
"""
import numpy as np
import gym
from gym import wrappers

malzantot

"""
Q-Learning example using OpenAI gym MountainCar enviornment
Author: Moustafa Alzantot (malzantot@ucla.edu)
"""
import numpy as np

import gym
from gym import wrappers

n_states = 50

malzantot

import numpy as np
import random
import time
import gym
from gym import wrappers

def run_episode(env, policy, episode_len=100):
    total_reward = 0
    obs = env.reset()
    for t in range(episode_len):

malzantot

import numpy as np
import time

import gym

def run_episode(env, policy, episode_len=100, render=False):
    total_reward = 0
    obs = env.reset()
    for t in range(episode_len):
        if render:

malzantot

import gym
import numpy as np

def gen_random_policy():
	return (np.random.uniform(-1,1, size=4), np.random.uniform(-1,1))

def policy_to_action(env, policy, obs):
    if np.dot(policy[0], obs) + policy[1] > 0:
    	return 1
    else:

malzantot

import gym

env = gym.make('CartPole-v0')

# Restart the environment to start a new episode
obs = env.reset()

for step_idx in range(500):
  env.render()
  obs, reward, done, _ = env.step(env.action_space.sample())