Cart-Pole soved after 4 episodes

CartPole-v0_ilovelinux_reproduced_klosowski.py

# CartPole-v0

# A pole is attached by an un-actuated joint to a cart,
# which moves along a frictionless track. The system 
# is controlled by applying a force of +1 or -1 to the 
# cart. The pendulum starts upright, and the goal is to 
# prevent it from falling over. A reward of +1 is provided 
# for every timestep that the pole remains upright. 
# The episode ends when the pole is more than 15 degrees 
# from vertical, or the cart moves more than 2.4 units from 
# the center.

import gym
import numpy

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

# This line creates a param value as a ramdon array[4]
param = numpy.random.rand(4) - 0.5

# This line creates a monitor
env.monitor.start('/tmp/OpenAI-CartPole', force=True)

best_reward = 0

for x in range(1000):
	observation = env.reset()
	total_reward = 0
	
	while True:
		action = numpy.dot(param, observation)
		action = 1 if action > 0 else 0
		observation, reward, done, info = env.step(action)
		total_reward += reward
		if done:
			if total_reward > best_reward:
				best_reward = total_reward
				param += observation
			elif total_reward < 200:
				param -= observation
			break

env.monitor.close()

# Code based in the code posted by @ilovelinux